Image Processing

Image Processing

PDF generated using the open source mwlib toolkit. See http://code.pediapress.com/ for more information.
PDF generated at: Thu, 27 May 2010 21:40:25 UTC

Contents
Articles
Introduction 1
Image 1
Pixel 2
Image processing 9
Digital image processing 11
Optical character recognition 14

Applications 18
Computer vision 18
Optical sorting 25
Augmented Reality 26
Face detection 37
Feature detection (computer vision) 39
Lane departure warning system 44
Non-photorealistic rendering 47
Medical image processing 50
Microscope image processing 57
Morphological image processing 59
Remote sensing 67
Medical imaging 74

References
Article Sources and Contributors 81
Image Sources, Licenses and Contributors 83

Article Licenses
License 84

1

Introduction

Image
An image (from Latin imago) is an artifact, for example a
two-dimensional picture, that has a similar appearance to some
subject—usually a physical object or a person.

Characteristics
Images may be two-dimensional, such as a photograph, screen display, Definition of image and imagery, from Thomas
and as well as a three-dimensional, such as a statue. They may be Blount's Glossographia Anglicana Nova, 1707.

captured by optical devices—such as cameras, mirrors, lenses,
telescopes, microscopes, etc. and natural objects and phenomena, such
as the human eye or water surfaces.
The word image is also used in the broader sense of any
two-dimensional figure such as a map, a graph, a pie chart, or an
abstract painting. In this wider sense, images can also be rendered
manually, such as by drawing, painting, carving, rendered
automatically by printing or computer graphics technology, or
developed by a combination of methods, especially in a
pseudo-photograph.

A volatile image is one that exists only for a short period of time. This
may be a reflection of an object by a mirror, a projection of a camera
obscura, or a scene displayed on a cathode ray tube. A fixed image,
also called a hard copy, is one that has been recorded on a material
object, such as paper or textile by photography or digital processes.
A mental image exists in an individual's mind: something one
remembers or imagines. The subject of an image need not be real; it
may be an abstract concept, such as a graph, function, or "imaginary"
entity. For example, Sigmund Freud claimed to have dreamed purely in
aural-images of dialogs. The development of synthetic acoustic
technologies and the creation of sound art have led to a consideration The top image is captured using photography.
of the possibilities of a sound-image made up of irreducible phonic The bottom image is rendered. Images are
produced by capturing or rendering.
substance beyond linguistic or musicological analysis.

A still image is a single static image, as distinguished from a moving image (see below). This phrase is used in
photography, visual media and the computer industry to emphasize that one is not talking about movies, or in very
precise or pedantic technical writing such as a standard.
A film still is a photograph taken on the set of a movie or television program during production, used for
promotional purposes.

Image 2

Moving image
A moving image is typically a movie (film), or video, including digital video. It could also be an animated display
such as a zoetrope.

See also
• Cinematography
• Mental image
• Painting
• Photography

External links
• The B-Z Reaction: The Moving or the Still Image? [1]
• FACE: Friends of Active Copyright Education [2]
• Library of Congress - Format Descriptions for Still Images [3]

References
[1] http:/ / www. apple. com/ science/ insidetheimage/ bzreaction/
[2] http:/ / www. csusa. org/ face/ home. htm
[3] http:/ / www. digitalpreservation. gov/ formats/ fdd/ still_fdd. shtml

Pixel
In digital imaging, a pixel (or picture element[1] ) is a single point in a
raster image. The pixel is the smallest addressable screen element; it is
the smallest unit of picture that can be controlled. Each pixel has its
own address. The address of a pixel corresponds to its coordinates.
Pixels are normally arranged in a 2-dimensional grid, and are often
represented using dots or squares. Each pixel is a sample of an original
This example shows an image with a portion
image; more samples typically provide more accurate representations
greatly enlarged, in which the individual pixels
of the original. The intensity of each pixel is variable. In color image are rendered as little squares and can easily be
systems, a color is typically represented by three or four component seen.
intensities such as red, green, and blue, or cyan, magenta, yellow, and
black.

In some contexts (such as descriptions of camera sensors), the term pixel is used to refer to a single scalar element of
a multi-component representation (more precisely called a photosite in the camera sensor context, although the
neologism sensel is also sometimes used to describe the elements of a digital camera's sensor),[2] while in others the
term may refer to the entire set of such component intensities for a spatial position. In color systems that use chroma

Pixel 3

subsampling, the multi-component concept of a pixel can
become difficult to apply, since the intensity measures for the
different color components correspond to different spatial
areas in a such a representation.
The word pixel is based on a contraction of pix ("pictures")
and el (for "element"); similar formations with el for
"element" include the words: voxel[3] and texel.[3]

A photograph of sub-pixel display elements on a laptop's
LCD screen

Etymology
The word "pixel" was first published in 1965 by Frederic C. Billingsley of JPL (in Pasadena, CA), to describe the
picture elements of video images from space probes to the Moon and Mars. However, Billingsley did not coin the
term himself. Instead, he got the word "pixel" from Keith E. McFarland, at the Link Division of General Precision in
Palo Alto, who did not know where the word originated. McFarland said simply it was "in use at the time" (circa
1963).[4]
The word is a combination of picture and element, via pix. The word pix appeared in Variety magazine headlines in
1932, as an abbreviation for the word pictures, in reference to movies.[5] By 1938, "pix" was being used in reference
to still pictures by photojournalists.[4]
The concept of a "picture element" dates to the earliest days of television, for example as "Bildpunkt" (the German
word for pixel, literally picture point) in the 1888 German patent of Paul Nipkow. According to various etymologies,
the earliest publication of the term picture element itself was in Wireless World magazine in 1927,[6] though it had
been used earlier in various U.S. patents filed as early as 1911.[7]
Some authors explain pixel as picture cell, as early as 1972.[8] In video processing, pel is often used instead of
pixel.[9] For example, IBM used it in their Technical Reference for the original PC.

Words with similar etymologies
• Texel (texture element) and luxel (lux element) are words used to describe a pixel when it is used in specific
context (texturing and light mapping respectively)
• A voxel is a volume element, the 3D analogue of a 2D pixel.
• Surfels (surface elements) have the same naming pattern as pixels, but share more similarities with shrunken
triangles than expanded pixels.

Pixel 4

Technical
A pixel is generally thought of as the smallest single component of a
digital image. The definition is highly context-sensitive. For example,
there can be "printed pixels" in a page, or pixels carried by electronic
signals, or represented by digital values, or pixels on a display device,
or pixels in a digital camera (photosensor elements). This list is not A pixel does not need to be rendered as a small
exhaustive, and depending on context, there are several terms that are square. This image shows alternative ways of
reconstructing an image from a set of pixel
synonymous in particular contexts, such as pel, sample, byte, bit, dot,
values, using dots, lines, or smooth filtering.
spot, etc. The term "pixels" can be used in the abstract, or as a unit of
measure, in particular when using pixels as a measure of resolution,
such as: 2400 pixels per inch, 640 pixels per line, or spaced 10 pixels apart.

The measures dots per inch (dpi) and pixels per inch (ppi) are sometimes used interchangeably, but have distinct
meanings, especially for printer devices, where dpi is a measure of the printer's density of dot (e.g. ink droplet)
placement.[10] For example, a high-quality photographic image may be printed with 600 ppi on a 1200 dpi inkjet
printer.[11] Even higher dpi numbers, such as the 4800 dpi quoted by printer manufacturers since 2002, do not mean
much in terms of achievable resolution.[12]
The more pixels used to represent an image, the closer the result can resemble the original. The number of pixels in
an image is sometimes called the resolution, though resolution has a more specific definition. Pixel counts can be
expressed as a single number, as in a "three-megapixel" digital camera, which has a nominal three million pixels, or
as a pair of numbers, as in a "640 by 480 display", which has 640 pixels from side to side and 480 from top to
bottom (as in a VGA display), and therefore has a total number of 640 × 480 = 307,200 pixels or 0.3 megapixels.
The pixels, or color samples, that form a digitized image (such as a JPEG file used on a web page) may or may not
be in one-to-one correspondence with screen pixels, depending on how a computer displays an image. In computing,
an image composed of pixels is known as a bitmapped image or a raster image. The word raster originates from
television scanning patterns, and has been widely used to describe similar halftone printing and storage techniques.

Sampling patterns
For convenience, pixels are normally arranged in a regular two-dimensional grid. By using this arrangement, many
common operations can be implemented by uniformly applying the same operation to each pixel independently.
Other arrangements of pixels are also possible, with some sampling patterns even changing the shape (or kernel) of
each pixel across the image. For this reason, care must be taken when acquiring an image on one device and
displaying it on another, or when converting image data from one pixel format to another.
For example:
• LCD screens typically use a staggered grid, where
the red, green, and blue components are sampled at
slightly different locations. Subpixel rendering is a
technology which takes advantage of these
differences to improve the rendering of text on LCD Text rendered using Cleartype
screens.
• Some digital cameras use a Bayer filter, resulting in a regular grid of pixels where the color of each pixel depends
on its position on the grid.
• A clipmap uses a hierarchical sampling pattern, where the size of the support of each pixel depends on its location
within the hierarchy.
• Warped grids are used when the underlying geometry is non-planar, such as images of the earth from space.[13]
• The use of non-uniform grids is an active research area, attempting to bypass the traditional Nyquist limit.[14]

Pixel 5

• Pixels on computer monitors are normally "square" (this is, having equal horizontal and vertical sampling pitch);
pixels in other systems are often "rectangular" (that is, having unequal horizontal and vertical sampling pitch –
oblong in shape), as are digital video formats with diverse aspect ratios, such as the anamorphic widescreen
formats of the CCIR 601 digital video standard.

Display resolution vs. native resolution in computer monitors
Computers can use pixels to display an image, often an abstract image that represents a GUI. The resolution of this
image is called the display resolution and is determined by the video card of the computer. LCD computer monitors
also use pixels to display an image, and have a native resolution. Each pixel is made up of triads, with the number of
these triads determining the native resolution. On some CRT monitors, the beam sweep rate may be fixed, resulting
in a fixed native resolution. Most CRT monitors do not have a fixed beam sweep rate, meaning they don't have a
native resolution at all - instead they have a set of resolutions that are equally well supported.
To produce the sharpest images possible on an LCD, the user must ensure the display resolution of the computer
matches the native resolution of the monitor. On a CRT with a fixed beam sweep rate, you are required to use the
native resolution. On a CRT without this restriction, you may use any resolution supported by the monitor that
matches the monitor's physical aspect ratio and it will look fine. If the aspect ratio of the physical display and the
selected resolution are different, many different things can happen. On some LCDs, the monitor will stretch or
squash the image to fill the entire display. This can result in the image appearing blurry or jagged.
On others, the aspect ratio will be maintained while expanding the image to fit the display, resulting in black bars on
the top or sides of the image. This can also result in the image appearing blurry or jagged, depending on the native
resolution of the display and the selected resolution on the computer. For example, let's take the relatively common
case of a full-screen application written assuming a 4:3 aspect ratio running on a 16:10 aspect ratio widescreen
display. If the selected resolution were 1600×1200 and you were running it on a 1920×1200 display that maintains
aspect ratio while expanding the image to fit, the image would not look blurry, because each pixel in the 1600×1200
image maps to exactly 1 pixel on the 1920×1200 display. If the selected resolution were 1280×960, the display
would have to try to stretch the 960 pixels to fill 1200 pixels, which would mean each of the selected resolution
pixels needs to take up 1.25 pixels on the physical display. Since this can't be done, the monitor uses some scheme to
figure out how to distribute the colors from those 960 pixels to fill the 1200 pixels of the physical display. This
mapping results in a blurry or jagged appearance. However, if the selected resolution were 800×600, you would be
OK again, because 600 pixels can be expanded to 1200 pixels by having each pixel from the selected resolution take
up 2 pixels on the physical display.
On yet other LCD monitors, if the selected resolution is less than the native resolution of the monitor, the monitor
will display things in the selected resolution, with a black border around the edges.

Bits per pixel
The number of distinct colors that can be represented by a pixel depends on the number of bits per pixel (bpp). A 1
bpp image uses 1-bit for each pixel, so each pixel can be either on or off. Each additional bit doubles the number of
colors available, so a 2 bpp image can have 4 colors, and a 3 bpp image can have 8 colors:
• 1 bpp, 21 = 2 colors (monochrome)
• 2 bpp, 22 = 4 colors
• 3 bpp, 23 = 8 colors
...
• 8 bpp, 28 = 256 colors
• 16 bpp, 216 = 65,536 colors ("Highcolor" )
• 24 bpp, 224 ≈ 16.8 million colors ("Truecolor")

Pixel 6

For color depths of 15 or more bits per pixel, the depth is normally the sum of the bits allocated to each of the red,
green, and blue components. Highcolor, usually meaning 16 bpp, normally has five bits for red and blue, and six bits
for green, as the human eye is more sensitive to errors in green than in the other two primary colors. For applications
involving transparency, the 16 bits may be divided into five bits each of red, green, and blue, with one bit left for
transparency. A 24-bit depth allows 8 bits per component. On some systems, 32-bit depth is available: this means
that each 24-bit pixel has an extra 8 bits to describe its opacity (for purposes of combining with another image).

Subpixels
Many display and image-acquisition systems are, for various
reasons, not capable of displaying or sensing the different color
channels at the same site. Therefore, the pixel grid is divided into
single-color regions that contribute to the displayed or sensed
color when viewed at a distance. In some displays, such as LCD,
LED, and plasma displays, these single-color regions are
separately addressable elements, which have come to be known as
subpixels. For example, LCDs typically divide each pixel
horizontally into three subpixels. When the square pixel is divided
into three subpixels, each subpixel is necessarily rectangular. In
the display industry terminology, subpixels are often referred to as
pixels, as they are the basic addressable elements in a viewpoint of
hardware, and they call pixel circuits rather than subpixel circuits.
Geometry of color elements of various CRT and LCD
Most digital camera image sensors also use single-color sensor displays; phosphor dots in a color CRT display (top
row) bear no relation to pixels or subpixels.
regions, for example using the Bayer filter pattern, and in the
camera industry these are known as pixels just like in the display
industry, not subpixels.
For systems with subpixels, two different approaches can be taken:
• The subpixels can be ignored, with full-color pixels being treated as the smallest addressable imaging element; or
• The subpixels can be included in rendering calculations, which requires more analysis and processing time, but
can produce apparently superior images in some cases.
This latter approach, referred to as subpixel rendering, uses knowledge of pixel geometry to manipulate the three
colored subpixels separately, producing a slight increase in the apparent resolution of color displays. While CRT
displays also use red-green-blue masked phosphor areas, dictated by a mesh grid called the shadow mask, it would
require a difficult calibration step to be aligned with the displayed pixel raster, and so CRTs do not currently use
subpixel rendering.

Megapixel
A megapixel (MP) is 1 million pixels, and is a term used not only for the number of pixels in an image, but also to
express the number of image sensor elements of digital cameras or the number of display elements of digital
displays. For example, a camera with an array of 2048×1536 sensor elements is commonly said to have "3.1
megapixels" (2048 × 1536 = 3,145,728). The megapixel count is often used as a figure of merit, though it is only one
of the figures that determines camera quality.
Digital cameras use photosensitive electronics, either charge-coupled device (CCD) or complementary
metal–oxide–semiconductor (CMOS) image sensors, consisting of a large number of single sensor elements, each of
which records a measured intensity level. In most digital cameras, the sensor array is covered with a patterned color
filter mosaic having red, green, and blue regions in the Bayer filter arrangement, so that each sensor element can

Pixel 7

record the intensity of a single primary color of light. The camera interpolates the color information of neighboring
sensor elements, through a process called demosaicing, to create the final image. These sensor elements are often
called "pixels", even though they only record 1 channel (only red, or green, or blue) of the final color image. Thus,
two of the three color channels for each sensor must be interpolated and a so-called N-megapixel camera that
produces an N-megapixel image provides only one-third of the information that an image of the same size could get
from a scanner. Thus, certain color contrasts may look fuzzier than others, depending on the allocation of the
primary colors (green has twice as many elements as red or blue in the Bayer arrangement).

Standard display resolutions
The display resolution of a digital television or display device is the number of distinct pixels in each dimension that
can be displayed. It can be an ambiguous term especially as the displayed resolution is controlled by all different
factors in cathode ray tube (CRT) and flat panel or projection displays using fixed picture-element (pixel) arrays.
One use of the term “display resolution” applies to fixed-pixel-array displays such as plasma display panels (PDPs),
liquid crystal displays (LCDs), Digital Light Processing (DLP) projectors, or similar technologies, and is simply the
physical number of columns and rows of pixels creating the display (e.g., 1920×1200). A consequence of having a
fixed grid display is that, for multi-format video inputs, all displays need a "scaling engine" (a digital video processor
that includes a memory array) to match the incoming picture format to the display.
Note that the use of the word resolution here is misleading. The term “display resolution” is usually used to mean
pixel dimensions (e.g., 1920×1200), which does not tell anything about the resolution of the display on which the
image is actually formed. In digital measurement the display resolution would be given in pixels per inch. In analog
measurement, if the screen is 10 inches high, then the horizontal resolution is measured across a square 10 inches
wide. This is typically stated as “xxx lines horizontal resolution, per picture height.” Example: Analog NTSC and
PAL TVs can typically display 480 (for NTSC) lines horizontal resolution, per picture height which is equivalent to
640 total lines from left-edge to right-edge.
Selected standard display resolutions
include:

Display standards comparison

Pixel 8

Name Megapixels Width x
Height

CGA 0.064 320×200

EGA 0.224 640×350

VGA 0.3 640×480

SVGA 0.5 800×600

XGA 0.8 1024×768

SXGA 1.3 1280×1024

UXGA 1.9 1600×1200

WUXGA 2.3 1920×1200

See also
• Computer display standard
• Gigapixel image
• Image resolution
• Intrapixel and Interpixel processing
• Pixel advertising
• Pixel art
• Pixel art scaling algorithms
• Pixel aspect ratio
• Point (typography)
• Raster scan
• Rasterisation
• Vector graphics
• Voxel

External links
• A Pixel Is Not A Little Square [15]: Microsoft Memo by computer graphics pioneer Alvy Ray Smith.
• Pixels and Me [16]: Video of a history talk at the Computer History Museum.
• Square and non-Square Pixels [17]: Technical info on pixel aspect ratios of modern video standards
(480i,576i,1080i,720p), plus software implications.

References
[1] Rudolf F. Graf (1999). Modern Dictionary of Electronics (http:/ / books. google. com/ books?id=o2I1JWPpdusC& pg=PA569& dq=pixel+
intitle:"Modern+ Dictionary+ of+ Electronics"+ inauthor:graf& lr=& as_brr=0& ei=5ygASM3qHoSgiwH45-GIDA&
sig=7tg-LuGdu6Njypaawi2bbkeq8pw). Oxford: Newnes. p. 569. ISBN 0-7506-43315. .
[2] Michael Goesele (2004). New Acquisition Techniques for Real Objects and Light Sources in Computer Graphics (http:/ / books. google. com/
books?id=ZTJJ8QzNv1wC& pg=PA33& dq=sensel+ sensor-element& lr=& as_brr=0& ei=t_-4R7WMPKCQtwOV-I2SBQ&
sig=nbPybOvZhWwQSt0uS0Rtq60mJlg). Books on Demand. ISBN 3833414898. .
[3] Foley, James D.; Andries van Dam, John F. Hughes, Steven K. Feiner (1990). "Spatial-partitioning representations; Surface detail". Computer
Graphics Principles and Practice. The Systems Programming Series. Addison-Wesley. ISBN 0-201-12110-7. "These cells are often called
voxels (volume elements), in analogy to pixels."
[4] Lyon, Richard F. (2006). A brief history of 'pixel' (http:/ / www. foveon. com/ files/ ABriefHistoryofPixel2. pdf). IS&T/SPIE Symposium on
Electronic Imaging.
[5] "Online Etymology Dictionary" (http:/ / www. etymonline. com/ index. php?search=pixel). .

Pixel 9

[6] "On language; Modem, I'm Odem" (http:/ / query. nytimes. com/ gst/ fullpage. html?res=990CE3DB1E31F931A35757C0A963958260), The
New York Times, April 2, 1995. Accessed April 7, 2008.
[7] Sinding-Larsen, Alf Transmission of Pictures of Moving Objects (http:/ / www. google. com/ patents?vid=USPAT1175313&
id=Df9EAAAAEBAJ& dq="picture+ element"& as_drrb_ap=b), US Patent 1,175,313, issued March 14, 1916.
[8] Robert L. Lillestrand (1972). "Techniques for Change Detection". IEEE Trans. Computers C-21 (7).
[9] Lewis, Peter H. (February 12, 1989). The Executive Computer; Compaq Sharpens Its Video Option (http:/ / www. nytimes. com/ 1989/ 02/
12/ business/ the-executive-computer-compaq-sharpens-its-video-option. html). The New York Times.
[10] Derek Doeffinger (2005). The Magic of Digital Printing (http:/ / books. google. com/ books?id=s2hIx1amJUcC& pg=PA24& dq=printer+
dots-per-inch+ pixels-per-inch& ei=ilKfSKjyBYm6tQPAu9WdBQ& sig=ACfU3U1img9C-r3_16xNKoYjTubg02GyVA). Lark Books. p. 24.
ISBN 1579906893. .
[11] "Experiments with Pixels Per Inch (PPI) on Printed Image Sharpness" (http:/ / www. clarkvision. com/ imagedetail/ printer-ppi/ ).
ClarkVision.com. July 3, 2005. .
[12] Harald Johnson (2002). Mastering Digital Printing (http:/ / books. google. com/ books?id=wto19gxFyfQC& pg=PA40& dq=inkjet+
printer+ 4800+ dpi+ addressability& lr=& as_brr=3& ei=ZI-kSITKAo3sswO7g-2dBQ&
sig=ACfU3U2RdAVkFq_0rsmQK6QwKPcDveJcxg#PPA41,M1). Thomson Course Technology. p. 40. ISBN 1929685653. .
[13] "Image registration of blurred satellite images" (http:/ / staff. utia. cas. cz/ zitova/ registration. htm). . Retrieved 2008-05-09.
[14] "ScienceDirect - Pattern Recognition: Image representation by a new optimal non-uniform morphological sampling:" (http:/ / www.
sciencedirect. com/ science/ article/ B6V14-3YXB1T5-8/ 2/ 15b559f2aefbc7bdc54c55df148c2374). . Retrieved 2008-05-09.
[15] http:/ / www. alvyray. com/ memos/ 6_pixel. pdf
[16] http:/ / video. google. com/ videoplay?docid=-5655850487750051532
[17] http:/ / lurkertech. com/ lg/ pixelaspect/

Image processing
In electrical engineering and computer
science, image processing is any form of
signal processing for which the input is an
image, such as photographs or frames of
video; the output of image processing can be
either an image or a set of characteristics or
parameters related to the image. Most
image-processing techniques involve
treating the image as a two-dimensional
signal and applying standard
signal-processing techniques to it.

Image processing usually refers to digital
image processing, but optical and analog
image processing are also possible. This
Monochrome black/white image
article is about general techniques that apply
to all of them. The acquisition of images
(producing the input image in the first place) is referred to as imaging.

Image processing 10

Typical operations
Among many other image processing
operations are:
• Euclidean geometry transformations such
as enlargement, reduction, and rotation
• Color corrections such as brightness and
contrast adjustments, color mapping, The red, green, and blue color channels of a photograph by Sergei Mikhailovich
Prokudin-Gorskii. The fourth image is a composite.
color balancing, quantization, or color
translation to a different color space
• Digital compositing or optical compositing (combination of two or more images). Used in film-making to make a
"matte"
• Interpolation, demosaicing, and recovery of a full image from a raw image format using a Bayer filter pattern
• Image registration, the alignment of two or more images
• Image differencing and morphing
• Image recognition, for example, extract the text from the image using optical character recognition or checkbox
and bubble values using optical mark recognition
• Image segmentation
• High dynamic range imaging by combining multiple images
• Geometric hashing for 2-D object recognition with affine invariance

Applications
• Computer vision
• Optical sorting
• Augmented Reality
• Face detection
• Feature detection
• Lane departure warning system
• Non-photorealistic rendering
• Medical image processing
• Microscope image processing
• Morphological image processing
• Remote sensing

See also
• Imaging
• Photo manipulation
• List of image analysis software
• Near sets
• Multidimensional systems

Image processing 11

Further reading
• Tinku Acharya and Ajoy K. Ray. Image Processing - Principles and Applications [1]. Wiley InterScience.
• Wilhelm Burger and Mark J. Burge (2007). Digital Image Processing: An Algorithmic Approach Using Java [2].
Springer. ISBN 1846283795 and ISBN 3540309403.
• R. Fisher, K Dawson-Howe, A. Fitzgibbon, C. Robertson, E. Trucco (2005). Dictionary of Computer Vision and
Image Processing. John Wiley. ISBN 0-470-01526-8.
• Bernd Jähne (2002). Digital Image Processing. Springer. ISBN 3-540-67754-2.
• Tim Morris (2004). Computer Vision and Image Processing. Palgrave Macmillan. ISBN 0-333-99451-5.
• Milan Sonka, Vaclav Hlavac and Roger Boyle (1999). Image Processing, Analysis, and Machine Vision. PWS
Publishing. ISBN 0-534-95393-X.

External links
• Lectures on Image Processing [3], by Alan Peters. Vanderbilt University. Updated 28 April 2008.
• EURASIP Journal on Image and Video Processing [4] — Open Access journal on Image Processing
• Image processing algorithms, implementations and demonstrations [5]

References
[1] http:/ / books. google. co. in/ books?id=smBw4-xvfrIC& lpg=PP1& ots=FVFYaOATEF& dq=image%20processing%20ajoy%20ray&
pg=PP1#v=onepage& q=& f=false
[2] http:/ / www. imagingbook. com/
[3] http:/ / www. archive. org/ details/ Lectures_on_Image_Processing
[4] http:/ / www. hindawi. com/ journals/ ivp/
[5] http:/ / www. ipol. im/

Digital image processing
Digital image processing is the use of computer algorithms to perform image processing on digital images. As a
subfield of digital signal processing, digital image processing has many advantages over analog image processing; it
allows a much wider range of algorithms to be applied to the input data, and can avoid problems such as the build-up
of noise and signal distortion during processing. Since images are defined over two dimensions (perhaps more)
digital image processing can be modeled in the form of Multidimensional Systems.

History
Many of the techniques of digital image processing, or digital picture processing as it was often called, were
developed in the 1960s at the Jet Propulsion Laboratory, MIT, Bell Labs, University of Maryland, and a few other
places, with application to satellite imagery, wirephoto standards conversion, medical imaging, videophone,
character recognition, and photo enhancement.[1] But the cost of processing was fairly high with the computing
equipment of that era. In the 1970s, digital image processing proliferated, when cheaper computers and dedicated
hardware became available. Images could then be processed in real time, for some dedicated problems such as
television standards conversion. As general-purpose computers became faster, they started to take over the role of
dedicated hardware for all but the most specialized and compute-intensive operations.
With the fast computers and signal processors available in the 2000s, digital image processing has become the most
common form of image processing, and is generally used because it is not only the most versatile method, but also
the cheapest.


Digital image processing technology for medical applications was inducted into the Space Foundation Space
Technology Hall of Fame in 1994.[2]

Tasks
Digital image processing allows the use of much more complex algorithms for image processing, and hence can
offer both more sophisticated performance at simple tasks, and the implementation of methods which would be
impossible by analog means.
In particular, digital image processing is the only practical technology for:
• Classification
• Feature extraction
• Pattern recognition
• Projection
• Multi-scale signal analysis
Some techniques which are used in digital image processing include:
• Pixelization
• Linear filtering
• Principal components analysis
• Independent component analysis
• Hidden Markov models
• Partial differential equations
• Self-organizing maps
• Neural networks
• Wavelets

Applications

Digital camera images
Digital cameras generally include dedicated digital image processing chips to convert the raw data from the image
sensor into a color-corrected image in a standard image file format. Images from digital cameras often receive further
processing to improve their quality, a distinct advantage digital cameras have over film cameras. The digital image
processing is typically done by special software programs that can manipulate the images in many ways.
Many digital cameras also enable viewing of histograms of images, as an aid for the photographer to better
understand the rendered brightness range of each shot.

Film
Westworld (1973) was the first feature film to use digital image processing to pixellate photography to simulate an
android's point of view.[3]

See also
• Computer graphics
• Computer vision
• Digitizing
• Endrov
• GPGPU
• ImageJ


• FIJI (software)
• Homomorphic filtering
• OpenCV
• Standard test image
• Super-resolution
• Multidimensional systems

Further reading

External links
• Tutorial for image processing [4] (contains a Java applet)
• Image processing algorithms, implementations and demonstrations [5]

References
[1] Azriel Rosenfeld, Picture Processing by Computer, New York: Academic Press, 1969
[2] "Space Technology Hall of Fame:Inducted Technologies/1994" (http:/ / www. spacetechhalloffame. org/
inductees_1994_Digital_Image_Processing. html). Space Foundation. 1994. . Retrieved 7 January 2010.
[3] A Brief, Early History of Computer Graphics in Film (http:/ / www. beanblossom. in. us/ larryy/ cgi. html), Larry Yaeger, 16 Aug 2002 (last
update), retrieved 24 March 2010
[4] http:/ / www. ph. tn. tudelft. nl/ Courses/ FIP/ frames/ fip. html


Optical character recognition
Optical character recognition, usually abbreviated to OCR, is the mechanical or electronic translation of scanned
images of handwritten, typewritten or printed text into machine-encoded text. It is widely used to convert books and
documents into electronic files, to computerize a record-keeping system in an office, or to publish the text on a
website. OCR makes it possible to edit the text, search for a word or phrase, store it more compactly, display or print
a copy free of scanning artifacts, and apply techniques such as machine translation, text-to-speech and text mining to
it. OCR is a field of research in pattern recognition, artificial intelligence and computer vision.
OCR systems require calibration to read a specific font; early versions needed to be programmed with images of
each character, and worked on one font at a time. "Intelligent" systems with a high degree of recognition accuracy
for most fonts are now common. Some systems are capable of reproducing formatted output that closely
approximates the original scanned page including images, columns and other non-textual components.

History
In 1929 Gustav Tauschek obtained a patent on OCR in Germany, followed by Handel who obtained a US patent on
OCR in USA in 1933 (U.S. Patent 1,915,993 [1]). In 1935 Tauschek was also granted a US patent on his method
(U.S. Patent 2,026,329 [2]). Tauschek's machine was a mechanical device that used templates and a photodetector.
In 1950, David H. Shepard, a cryptanalyst at the Armed Forces Security Agency in the United States, addressed the
problem of converting printed messages into machine language for computer processing and built a machine to do
this, reported in the Washington Daily News on 27 April 1951 and in the New York Times on 26 December 1953
after his U.S. Patent 2,663,758 [3] was issued. Shepard then founded Intelligent Machines Research Corporation
(IMR), which went on to deliver the world's first several OCR systems used in commercial operation.
The first commercial system was installed at the Readers Digest in 1955. The second system was sold to the
Standard Oil Company for reading credit card imprints for billing purposes. Other systems sold by IMR during the
late 1950s included a bill stub reader to the Ohio Bell Telephone Company and a page scanner to the United States
Air Force for reading and transmitting by teletype typewritten messages. IBM and others were later licensed on
Shepard's OCR patents.
In about 1965 Readers Digest and RCA collaborated to build an OCR Document reader designed to digitize the
serial numbers on Reader Digest coupons returned from advertisements. The font used on the documents were
printed by an RCA Drum printer using the OCR-A font. The reader was connected directly to an RCA 301 computer
(one of the first solid state computers). This reader was followed by a specialized document reader installed at TWA
where the reader processed Airline Ticket stock. The readers processed document at a rate of 1,500 documents per
minute, and checked each document, rejecting those it was not able to process correctly. The product became part of
the RCA product line as a reader designed to process "Turn around Documents" such as those Utility and insurance
bills returned with payments.
The United States Postal Service has been using OCR machines to sort mail since 1965 based on technology devised
primarily by the prolific inventor Jacob Rabinow. The first use of OCR in Europe was by the British General Post
Office (GPO). In 1965 it began planning an entire banking system, the National Giro, using OCR technology, a
process that revolutionized bill payment systems in the UK. Canada Post has been using OCR systems since 1971.
OCR systems read the name and address of the addressee at the first mechanized sorting center, and print a routing
bar code on the envelope based on the postal code. To avoid confusion with the human-readable address field which
can be located anywhere on the letter, special ink (orange in visible light) is used that is clearly visible under
ultraviolet light. Envelopes may then be processed with equipment based on simple barcode readers.
In 1974 Ray Kurzweil started the company Kurzweil Computer Products, Inc. and led development of the first
omni-font optical character recognition system — a computer program capable of recognizing text printed in any


normal font. He decided that the best application of this technology would be to create a reading machine for the
blind, which would allow blind people to have a computer read text to them out loud. This device required the
invention of two enabling technologies — the CCD flatbed scanner and the text-to-speech synthesizer. On January
13, 1976 the successful finished product was unveiled during a widely-reported news conference headed by
Kurzweil and the leaders of the National Federation of the Blind.
In 1978 Kurzweil Computer Products began selling a commercial version of the optical character recognition
computer program. LexisNexis was one of the first customers, and bought the program to upload paper legal and
news documents onto its nascent online databases. Two years later, Kurzweil sold his company to Xerox, which had
an interest in further commercializing paper-to-computer text conversion. Kurzweil Computer Products became a
subsidiary of Xerox known as Scansoft, now Nuance Communications.

Current state of OCR technology
The accurate recognition of Latin-script, typewritten text is now considered largely a solved problem on applications
where clear imaging is available such as scanning of printed documents. Typical accuracy rates on these exceed
99%; total accuracy can only be achieved by human review. Other areas—including recognition of hand printing,
cursive handwriting, and printed text in other scripts (especially those with a very large number of characters)—are
still the subject of active research.
Accuracy rates can be measured in several ways, and how they are measured can greatly affect the reported accuracy
rate. For example, if word context (basically a lexicon of words) is not used to correct software finding non-existent
words, a character error rate of 1% (99% accuracy) may result in an error rate of 5% (95% accuracy) or worse if the
measurement is based on whether each whole word was recognized with no incorrect letters[4] .
On-line character recognition is sometimes confused with Optical Character Recognition[5] (see Handwriting
recognition). OCR is an instance of off-line character recognition, where the system recognizes the fixed static shape
of the character, while on-line character recognition instead recognizes the dynamic motion during handwriting. For
example, on-line recognition, such as that used for gestures in the Penpoint OS or the Tablet PC can tell whether a
horizontal mark was drawn right-to-left, or left-to-right. On-line character recognition is also referred to by other
terms such as dynamic character recognition, real-time character recognition, and Intelligent Character Recognition
or ICR.
On-line systems for recognizing hand-printed text on the fly have become well-known as commercial products in
recent years (see Tablet PC history). Among these are the input devices for personal digital assistants such as those
running Palm OS. The Apple Newton pioneered this product. The algorithms used in these devices take advantage of
the fact that the order, speed, and direction of individual lines segments at input are known. Also, the user can be
retrained to use only specific letter shapes. These methods cannot be used in software that scans paper documents, so
accurate recognition of hand-printed documents is still largely an open problem. Accuracy rates of 80% to 90% on
neat, clean hand-printed characters can be achieved, but that accuracy rate still translates to dozens of errors per
page, making the technology useful only in very limited applications.
Recognition of cursive text is an active area of research, with recognition rates even lower than that of hand-printed
text. Higher rates of recognition of general cursive script will likely not be possible without the use of contextual or
grammatical information. For example, recognizing entire words from a dictionary is easier than trying to parse
individual characters from script. Reading the Amount line of a cheque (which is always a written-out number) is an
example where using a smaller dictionary can increase recognition rates greatly. Knowledge of the grammar of the
language being scanned can also help determine if a word is likely to be a verb or a noun, for example, allowing
greater accuracy. The shapes of individual cursive characters themselves simply do not contain enough information
to accurately (greater than 98%) recognize all handwritten cursive script.
It is necessary to understand that OCR technology is a basic technology also used in advanced scanning applications.
Due to this, an advanced scanning solution can be unique and patented and not easily copied despite being based on


this basic OCR technology.
For more complex recognition problems, intelligent character recognition systems are generally used, as artificial
neural networks can be made indifferent to both affine and non-linear transformations.[6]
A technique which is having considerable success in recognising difficult words and character groups within
documents generally amenable to computer OCR is to submit them automatically to humans in the reCAPTCHA
system.

OCR software
OCR Software and ICR Software technology are analytical artificial intelligence systems that consider sequences of
characters rather than whole words or phrases. Based on the analysis of sequential lines and curves, OCR and ICR
make 'best guesses' at characters using database look-up tables to closely associate or match the strings of characters
that form words.

See also
• Automatic number plate recognition
• CAPTCHA
• Computational linguistics
• Computer vision
• Digital Mailroom
• Machine learning
• Music OCR
• OCR SDK
• OCR Software
• Optical mark recognition
• Raster to vector
• Raymond Kurzweil
• Speech recognition
• Book scanning
• Institutional Repository
• Digital Library
• OCR-B

External links
• 17 Things [7] Explanation of basic handwriting recognition principles and history
• Unicode OCR - Hex Range: 2440-245F [8] Optical Character Recognition in Unicode
• Free Online OCR [9] Free Online OCR

References
[1] http:/ / www. google. com/ patents?q=1,915,993
[4] Suen, C.Y., et al (1987-05-29), Future Challenges in Handwriting and Computer Applications (http:/ / users. erols. com/ rwservices/ pens/
biblio88. html#Suen88), 3rd International Symposium on Handwriting and Computer Applications, Montreal, May 29, 1987, , retrieved
2008-10-03
[5] Tappert, Charles C., et al (1990-08), The State of the Art in On-line Handwriting Recognition (http:/ / users. erols. com/ rwservices/ pens/
biblio90. html#Tappert90c), IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol 12 No 8, August 1990, pp 787-ff, ,
retrieved 2008-10-03


[6] LeNet-5, Convolutional Neural Networks (http:/ / yann. lecun. com/ exdb/ lenet/ )
[7] http:/ / technology. 17things. com/ what-is-handwriting-recognition. html
[8] http:/ / www. unicode. org/ charts/ PDF/ U2440. pdf
[9] http:/ / www. free-online-ocr. com

18

Applications

Computer vision
Computer vision is the science and technology of machines that see. As a scientific discipline, computer vision is
concerned with the theory behind artificial systems that extract information from images. The image data can take
many forms, such as video sequences, views from multiple cameras, or multi-dimensional data from a medical
scanner.
As a technological discipline, computer vision seeks to apply its theories and models to the construction of computer
vision systems. Examples of applications of computer vision include systems for:
• Controlling processes (e.g., an industrial robot or an autonomous vehicle).
• Detecting events (e.g., for visual surveillance or people counting).
• Organizing information (e.g., for indexing databases of images and image sequences).
• Modeling objects or environments (e.g., industrial inspection, medical image analysis or topographical modeling).
• Interaction (e.g., as the input to a device for computer-human interaction).
Computer vision is closely related to the study of biological vision. The field of biological vision studies and models
the physiological processes behind visual perception in humans and other animals. Computer vision, on the other
hand, studies and describes the processes implemented in software and hardware behind artificial vision systems.
Interdisciplinary exchange between biological and computer vision has proven fruitful for both fields.
Computer vision is, in some ways, the inverse of computer graphics. While computer graphics produces image data
from 3D models, computer vision often produces 3D models from image data. There is also a trend towards a
combination of the two disciplines, e.g., as explored in augmented reality.
Sub-domains of computer vision include scene reconstruction, event detection, video tracking, object recognition,
learning, indexing, motion estimation, and image restoration.

State of the art
Computer vision is a diverse and relatively new field of study. In the early days of computing, it was difficult to
process even moderately large sets of image data. It was not until the late 1970s that a more focused study of the
field emerged. Computer vision covers a wide range of topics which are often related to other disciplines, and
consequently there is no standard formulation of "the computer vision problem". Moreover, there is no standard
formulation of how computer vision problems should be solved. Instead, there exists an abundance of methods for
solving various well-defined computer vision tasks, where the methods often are very task specific and seldom can
be generalized over a wide range of applications. Many of the methods and applications are still in the state of basic
research, but more and more methods have found their way into commercial products, where they often constitute a
part of a larger system which can solve complex tasks (e.g., in the area of medical images, or quality control and
measurements in industrial processes). In most practical computer vision applications, the computers are
pre-programmed to solve a particular task, but methods based on learning are now becoming increasingly common.

Computer vision 19

Related fields
Much of artificial intelligence deals with autonomous planning or deliberation for robotical systems to navigate
through an environment. A detailed understanding of these environments is required to navigate through them.
Information about the environment could be provided by a computer vision system, acting as a vision sensor and
providing high-level information about the environment and the robot. Artificial intelligence and computer vision
share other topics such as pattern recognition and learning techniques. Consequently, computer vision is sometimes
seen as a part of the artificial intelligence field or the computer science field in general.
Physics is another field that is closely related to computer vision. Computer vision systems rely on image sensors
which detect electromagnetic radiation which is typically in the form of either visible or infra-red light. The sensors
are designed using solid-state physics. The process by which light propagates and reflects off surfaces is explained
using optics. Sophisticated image sensors even require quantum mechanics to provide a complete understanding of
the image formation process. Also, various measurement problems in physics can be addressed using computer
vision, for example motion in fluids.
A third field which plays an important role is neurobiology, specifically the study of the biological vision system.
Over the last century, there has been an extensive study of eyes, neurons, and the brain structures devoted to
processing of visual stimuli in both humans and various animals. This has led to a coarse, yet complicated,
description of how "real" vision systems operate in order to solve certain vision related tasks. These results have led
to a subfield within computer vision where artificial systems are designed to mimic the processing and behavior of
biological systems, at different levels of complexity. Also, some of the learning-based methods developed within
computer vision have their background in biology.
Yet another field related to computer vision is signal processing. Many methods for processing of one-variable
signals, typically temporal signals, can be extended in a natural way to processing of two-variable signals or
multi-variable signals in computer vision. However, because of the specific nature of images there are many methods
developed within computer vision which have no counterpart in the processing of one-variable signals. A distinct
character of these methods is the fact that they are non-linear which, together with the multi-dimensionality of the
signal, defines a subfield in signal processing as a part of computer vision.
Beside the above mentioned views on computer vision, many of the related research topics can also be studied from
a purely mathematical point of view. For example, many methods in computer vision are based on statistics,
optimization or geometry. Finally, a significant part of the field is devoted to the implementation aspect of computer
vision; how existing methods can be realized in various combinations of software and hardware, or how these
methods can be modified in order to gain processing speed without losing too much performance.
The fields most closely related to computer vision are image processing, image analysis and machine vision. There is
a significant overlap in the range of techniques and applications that these cover. This implies that the basic
techniques that are used and developed in these fields are more or less identical, something which can be interpreted
as there is only one field with different names. On the other hand, it appears to be necessary for research groups,
scientific journals, conferences and companies to present or market themselves as belonging specifically to one of
these fields and, hence, various characterizations which distinguish each of the fields from the others have been
presented.
The following characterizations appear relevant but should not be taken as universally accepted:
• Image processing and image analysis tend to focus on 2D images, how to transform one image to another, e.g., by
pixel-wise operations such as contrast enhancement, local operations such as edge extraction or noise removal, or
geometrical transformations such as rotating the image. This characterization implies that image
processing/analysis neither require assumptions nor produce interpretations about the image content.
• Computer vision tends to focus on the 3D scene projected onto one or several images, e.g., how to reconstruct
structure or other information about the 3D scene from one or several images. Computer vision often relies on

Computer vision 20

more or less complex assumptions about the scene depicted in an image.
• Machine vision tends to focus on applications, mainly in manufacturing, e.g., vision based autonomous robots and
systems for vision based inspection or measurement. This implies that image sensor technologies and control
theory often are integrated with the processing of image data to control a robot and that real-time processing is
emphasized by means of efficient implementations in hardware and software. It also implies that the external
conditions such as lighting can be and are often more controlled in machine vision than they are in general
computer vision, which can enable the use of different algorithms.
• There is also a field called imaging which primarily focus on the process of producing images, but sometimes also
deals with processing and analysis of images. For example, medical imaging contains lots of work on the analysis
of image data in medical applications.
• Finally, pattern recognition is a field which uses various methods to extract information from signals in general,
mainly based on statistical approaches. A significant part of this field is devoted to applying these methods to
image data.

Applications for computer vision
One of the most prominent application fields is medical computer vision or medical image processing. This area is
characterized by the extraction of information from image data for the purpose of making a medical diagnosis of a
patient. Generally, image data is in the form of microscopy images, X-ray images, angiography images, ultrasonic
images, and tomography images. An example of information which can be extracted from such image data is
detection of tumours, arteriosclerosis or other malign changes. It can also be measurements of organ dimensions,
blood flow, etc. This application area also supports medical research by providing new information, e.g., about the
structure of the brain, or about the quality of medical treatments.
A second application area in computer vision is in industry, sometimes called machine vision, where information is
extracted for the purpose of supporting a manufacturing process. One example is quality control where details or
final products are being automatically inspected in order to find defects. Another example is measurement of
position and orientation of details to be picked up by a robot arm. Machine vision is also heavily used in agricultural
process to remove undesirable food stuff from bulk material, a process called optical sorting.
Military applications are probably one of the largest areas for computer vision. The obvious examples are detection
of enemy soldiers or vehicles and missile guidance. More advanced systems for missile guidance send the missile to
an area rather than a specific target, and target selection is made when the missile reaches the area based on locally
acquired image data. Modern military concepts, such as "battlefield awareness", imply that various sensors,
including image sensors, provide a rich set of information about a combat scene which can be used to support
strategic decisions. In this case, automatic processing of the data is used to reduce complexity and to fuse
information from multiple sensors to increase reliability.

Computer vision 21

One of the newer application areas is autonomous vehicles, which
include submersibles, land-based vehicles (small robots with
wheels, cars or trucks), aerial vehicles, and unmanned aerial
vehicles (UAV). The level of autonomy ranges from fully
autonomous (unmanned) vehicles to vehicles where computer
vision based systems support a driver or a pilot in various
situations. Fully autonomous vehicles typically use computer
vision for navigation, i.e. for knowing where it is, or for producing
a map of its environment (SLAM) and for detecting obstacles. It
can also be used for detecting certain task specific events, e. g., a
UAV looking for forest fires. Examples of supporting systems are Artist's Concept of Rover on Mars, an example of an
obstacle warning systems in cars, and systems for autonomous unmanned land-based vehicle. Notice the stereo
cameras mounted on top of the Rover. (credit: Maas
landing of aircraft. Several car manufacturers have demonstrated
Digital LLC)
systems for autonomous driving of cars, but this technology has
still not reached a level where it can be put on the market. There
are ample examples of military autonomous vehicles ranging from advanced missiles, to UAVs for recon missions or
missile guidance. Space exploration is already being made with autonomous vehicles using computer vision, e. g.,
NASA's Mars Exploration Rover and ESA's ExoMars Rover.

Other application areas include:
• Support of visual effects creation for cinema and broadcast, e.g., camera tracking (matchmoving).
• Surveillance.

Typical tasks of computer vision
Each of the application areas described above employ a range of computer vision tasks; more or less well-defined
measurement problems or processing problems, which can be solved using a variety of methods. Some examples of
typical computer vision tasks are presented below.

Recognition
The classical problem in computer vision, image processing, and machine vision is that of determining whether or
not the image data contains some specific object, feature, or activity. This task can normally be solved robustly and
without effort by a human, but is still not satisfactorily solved in computer vision for the general case: arbitrary
objects in arbitrary situations. The existing methods for dealing with this problem can at best solve it only for
specific objects, such as simple geometric objects (e.g., polyhedra), human faces, printed or hand-written characters,
or vehicles, and in specific situations, typically described in terms of well-defined illumination, background, and
pose of the object relative to the camera.
Different varieties of the recognition problem are described in the literature:
• Object recognition: one or several pre-specified or learned objects or object classes can be recognized, usually
together with their 2D positions in the image or 3D poses in the scene.
• Identification: An individual instance of an object is recognized. Examples: identification of a specific person's
face or fingerprint, or identification of a specific vehicle.
• Detection: the image data is scanned for a specific condition. Examples: detection of possible abnormal cells or
tissues in medical images or detection of a vehicle in an automatic road toll system. Detection based on relatively
simple and fast computations is sometimes used for finding smaller regions of interesting image data which can
be further analyzed by more computationally demanding techniques to produce a correct interpretation.
Several specialized tasks based on recognition exist, such as:

Computer vision 22

• Content-based image retrieval: finding all images in a larger set of images which have a specific content. The
content can be specified in different ways, for example in terms of similarity relative a target image (give me all
images similar to image X), or in terms of high-level search criteria given as text input (give me all images which
contains many houses, are taken during winter, and have no cars in them).
• Pose estimation: estimating the position or orientation of a specific object relative to the camera. An example
application for this technique would be assisting a robot arm in retrieving objects from a conveyor belt in an
assembly line situation.
• Optical character recognition (OCR): identifying characters in images of printed or handwritten text, usually
with a view to encoding the text in a format more amenable to editing or indexing (e.g. ASCII).

Motion analysis
Several tasks relate to motion estimation where an image sequence is processed to produce an estimate of the
velocity either at each points in the image or in the 3D scene, or even of the camera that produces the images .
Examples of such tasks are:
• Egomotion: determining the 3D rigid motion (rotation and translation) of the camera from an image sequence
produced by the camera.
• Tracking: following the movements of a (usually) smaller set of interest points or objects (e.g., vehicles or
humans) in the image sequence.
• Optical flow: to determine, for each point in the image, how that point is moving relative to the image plane, i.e.,
its apparent motion. This motion is a result both of how the corresponding 3D point is moving in the scene and
how the camera is moving relative to the scene.

Scene reconstruction
Given one or (typically) more images of a scene, or a video, scene reconstruction aims at computing a 3D model of
the scene. In the simplest case the model can be a set of 3D points. More sophisticated methods produce a complete
3D surface model.

Image restoration
The aim of image restoration is the removal of noise (sensor noise, motion blur, etc.) from images. The simplest
possible approach for noise removal is various types of filters such as low-pass filters or median filters. More
sophisticated methods assume a model of how the local image structures look like, a model which distinguishes them
from the noise. By first analysing the image data in terms of the local image structures, such as lines or edges, and
then controlling the filtering based on local information from the analysis step, a better level of noise removal is
usually obtained compared to the simpler approaches.

Computer vision systems
The organization of a computer vision system is highly application dependent. Some systems are stand-alone
applications which solve a specific measurement or detection problem, while others constitute a sub-system of a
larger design which, for example, also contains sub-systems for control of mechanical actuators, planning,
information databases, man-machine interfaces, etc. The specific implementation of a computer vision system also
depends on if its functionality is pre-specified or if some part of it can be learned or modified during operation.
There are, however, typical functions which are found in many computer vision systems.
• Image acquisition: A digital image is produced by one or several image sensors, which, besides various types of
light-sensitive cameras, include range sensors, tomography devices, radar, ultra-sonic cameras, etc. Depending on
the type of sensor, the resulting image data is an ordinary 2D image, a 3D volume, or an image sequence. The
pixel values typically correspond to light intensity in one or several spectral bands (gray images or colour

Computer vision 23

images), but can also be related to various physical measures, such as depth, absorption or reflectance of sonic or
electromagnetic waves, or nuclear magnetic resonance.
• Pre-processing: Before a computer vision method can be applied to image data in order to extract some specific
piece of information, it is usually necessary to process the data in order to assure that it satisfies certain
assumptions implied by the method. Examples are
• Re-sampling in order to assure that the image coordinate system is correct.
• Noise reduction in order to assure that sensor noise does not introduce false information.
• Contrast enhancement to assure that relevant information can be detected.
• Scale-space representation to enhance image structures at locally appropriate scales.
• Feature extraction: Image features at various levels of complexity are extracted from the image data. Typical
examples of such features are
• Lines, edges and ridges.
• Localized interest points such as corners, blobs or points.
More complex features may be related to texture, shape or motion.
• Detection/segmentation: At some point in the processing a decision is made about which image points or regions
of the image are relevant for further processing. Examples are
• Selection of a specific set of interest points
• Segmentation of one or multiple image regions which contain a specific object of interest.
• High-level processing: At this step the input is typically a small set of data, for example a set of points or an
image region which is assumed to contain a specific object. The remaining processing deals with, for example:
• Verification that the data satisfy model-based and application specific assumptions.
• Estimation of application specific parameters, such as object pose or object size.
• Classifying a detected object into different categories.

See also
• Active vision
• Artificial intelligence, Strong AI
• Digital image processing
• Image processing
• List of computer vision topics
• Machine learning
• Machine vision
• Machine vision glossary
• Medical imaging
• Pattern recognition
• Photogrammetry

Computer vision 24

Further reading
• Dana H. Ballard and Christopher M. Brown (1982). Computer Vision [1]. Prentice Hall. ISBN 0131653164.
• David Marr (1982). Vision. W. H. Freeman and Company. ISBN 0-7167-1284-9.
• Azriel Rosenfeld and Avinash Kak (1982). Digital Picture Processing. Academic Press. ISBN 0-12-597301-2.
• Berthold Klaus Paul Horn (1986). Robot Vision. MIT Press. ISBN 0-262-08159-8.
• Olivier Faugeras (1993). Three-Dimensional Computer Vision, A Geometric Viewpoint. MIT Press.
ISBN 0-262-06158-9.
• Tony Lindeberg (1994). Scale-Space Theory in Computer Vision [2]. Springer. ISBN 0-7923-9418-6.
• James L. Crowley and Henrik I. Christensen (Eds.) (1995). Vision as Process. Springer-Verlag.
ISBN 3-540-58143-X and ISBN 0-387-58143-X.
• Gösta H. Granlund and Hans Knutsson (1995). Signal Processing for Computer Vision. Kluwer Academic
Publisher. ISBN 0-7923-9530-1.
• Reinhard Klette, Karsten Schluens and Andreas Koschan (1998). Computer Vision - Three-Dimensional Data
from Images [3]. Springer, Singapore. ISBN 981-3083-71-9.
• Emanuele Trucco and Alessandro Verri (1998). Introductory Techniques for 3-D Computer Vision. Prentice Hall.
ISBN 0132611082.
• Bernd Jähne and Horst Haußecker (2000). Computer Vision and Applications, A Guide for Students and
Practitioners. Academic Press. ISBN 0-13-085198-1.
• Linda G. Shapiro and George C. Stockman (2001). Computer Vision. Prentice Hall. ISBN 0-13-030796-3.
• David A. Forsyth and Jean Ponce (2003). Computer Vision, A Modern Approach. Prentice Hall.
ISBN 0-12-379777-2.
• Richard Hartley and Andrew Zisserman (2003). Multiple View Geometry in Computer Vision. Cambridge
University Press. ISBN 0-521-54051-8.
• Gérard Medioni and Sing Bing Kang (2004). Emerging Topics in Computer Vision. Prentice Hall.
ISBN 0-13-101366-1.
• E. Roy Davies (2005). Machine Vision : Theory, Algorithms, Practicalities. Morgan Kaufmann.
ISBN 0-12-206093-8.
• Nikos Paragios and Yunmei Chen and Olivier Faugeras (2005). Handbook of Mathematical Models in Computer
Vision [4]. Springer. ISBN 0-387-26371-3.
• Pedram Azad, Tilo Gockel, Rüdiger Dillmann (2008). Computer Vision - Principles and Practice [5]. Elektor
International Media BV. ISBN 0905705718.

Computer vision 25

External links

General resources
• Keith Price's Annotated Computer Vision Bibliography [6] and the Official Mirror Site Keith Price's Annotated
Computer Vision Bibliography [7]
• USC Iris computer vision conference list [8]
• Computer Vision Online [9]
• Computer Vision Central [10]
• The Computer Vision Genealogy Project [11]

References
[1] http:/ / homepages. inf. ed. ac. uk/ rbf/ BOOKS/ BANDB/ bandb. htm
[2] http:/ / www. nada. kth. se/ ~tony/ book. html
[3] http:/ / www. cs. auckland. ac. nz/ ~rklette/ Books/ SpringerCV98/ Springer98. html
[4] http:/ / www. mas. ecp. fr/ vision/ Personnel/ nikos/ paragios-chen-faugeras/
[5] http:/ / ivt. sourceforge. net/ book. html
[6] http:/ / iris. usc. edu/ Vision-Notes/ bibliography/ contents. html
[7] http:/ / www. visionbib. com/ bibliography/ contents. html
[8] http:/ / iris. usc. edu/ Information/ Iris-Conferences. html
[9] http:/ / www. ComputerVisionOnline. com
[10] http:/ / www. ComputerVisionCentral. com
[11] http:/ / visiongenealogy. summerhost. info/

Optical sorting
Optical Sorting is a process of visually sorting a product though the use of Photodetector (light sensors), Camera[1] ,
or the standard Mark 1 Human eye ball[2] .
In its simplest operation, a machine will simply see how much light is reflected off the object using a simple
Photodetector (such as a Photoresistor) and accept or reject the item depending of how reflective it is (light or dark).
More sophisticated systems use Image processing to discriminate the colors of the object, often via a controlled
spectra of light, even beyond the visible spectrum into the IR and UV range. Shape detection is an evolving ability.
The common method of removal is jets of compressed air, but other exist.
The term "Optical sorting" also includes manual seeing and manipulating process.
Satake Corporation, Best [3], and Sortex [4] are three of several companies that build Optical Sorting machines.

References
[1] http:/ / www. woodheadpublishing. com/ en/ book. aspx?bookID=614& printer=yes Detecting foreign bodies in food
[2] "Image Processing for the Food Industry", E. R. Davis; World Scientific Publishing Co. Pte. Ltd.; London, 2000
[3] http:/ / www. bestnv. com/
[4] http:/ / www. buhlergroup. com/ 17217EN. asp


Augmented Reality
Augmented reality (AR) is a term for a live direct or indirect view of
a physical real-world environment whose elements are augmented by
virtual computer-generated imagery. It is related to a more general
concept called mediated reality in which a view of reality is modified
(possibly even diminished rather than augmented) by a computer. As a
result, the technology functions by enhancing one’s current perception
of reality.
Augmented GeoTravel for the iPhone 3GS uses
In the case of Augmented Reality, the augmentation is conventionally the compass, the GPS and the accelerometers to
in real-time and in semantic context with environmental elements, such show the Augmented Reality view

as sports scores on TV during a match. With the help of advanced AR
technology (e.g. adding computer vision and object recognition) the
information about the surrounding real world of the user becomes
interactive and digitally usable. Artificial information about the
environment and the objects in it can be stored and retrieved as an
information layer on top of the real world view. The term augmented
reality is believed to have been coined in 1990 by Thomas Caudell, an
employee of Boeing at the time[1] .

Augmented reality research explores the application of Wikitude World Browser on the iPhone 3GS uses
computer-generated imagery in live-video streams as a way to expand GPS and solid state compass

the real-world. Advanced research includes use of head-mounted
displays and virtual retinal displays for visualization purposes, and
construction of controlled environments containing any number of
sensors and actuators.

Definition
There are two commonly accepted definitions of Augmented Reality
today. One was given by Ronald Azuma in 1997 [2] . Azuma's
definition says that Augmented Reality
AR Tower Defense game on the Nokia N95
• combines real and virtual
smartphone (Symbian OS) uses fiduciary markers
• is interactive in real time
• is registered in 3D
Additionally Paul Milgram and Fumio Kishino defined Milgram's Reality-Virtuality Continuum in 1994 [3] . They
describe a continuum that spans from the real environment to a pure virtual environment. In between there are
Augmented Reality (closer to the real environment) and Augmented Virtuality (is closer to the virtual environment).
This continuum has been extended into a two-dimensional plane of
"Virtuality" and "Mediality"[4] . Taxonomy of Reality, Virtuality,
Mediality. The origin R denotes unmodified reality. A continuum
across the Virtuality axis V includes reality augmented with Milgram's Continuum
graphics (Augmented Reality), as well as graphics augmented by
reality (Augmented Virtuality). However, the taxonomy also


includes modification of reality or virtuality or any combination of
these. The modification is denoted by moving up the mediality
axis. Further up this axis, for example, we can find mediated
reality, mediated virtuality, or any combination of these. Further
up and to the right we have virtual worlds that are responsive to a
severely modified version of reality. (at right) Mediated reality
generalizes the concepts of mixed reality, etc.. It includes the
virtuality reality continuum (mixing) but also, in addition to
additive effects, also includes multiplicatave effects (modulation)
of (sometimes deliberately) diminished reality. Moreover, it
considers, more generally, that reality may be modified in various
ways. The mediated reality framework describes devices that
deliberately modify reality, as well as devices that accidentally Mediated Reality continuum showing four points:
modify it. Augmented Reality, Augmented Virtuality, Mediated
Reality, and Mediated Virtuality on the Virtuality and
More recently, the term augmented reality has been blurred a bit Mediality axes
due to the increased interest of the general public in AR.

Examples
Commonly known examples of AR are the yellow "first down" lines seen in television broadcasts of American
football games using the 1st & Ten system, and the colored trail showing location and direction of the puck in TV
broadcasts of ice hockey games. The real-world elements are the football field and players, and the virtual element is
the yellow line, which is drawn over the image by computers in real time. Similarly, rugby fields and cricket pitches
are branded by their sponsors using Augmented Reality; giant logos are inserted onto the fields when viewed on
television. In some cases, the modification of reality goes beyond mere augmentation. For example, advertisements
may be blocked out (partially or wholly diminished) and replaced with different advertisements. Such replacement is
an example of Mediated reality, a more general concept than AR.
Television telecasts of swimming events also often have a virtual line which indicates the position of the current
world record holder at that time.
Another type of AR application uses projectors and screens to insert objects into the real environment, enhancing
museum exhibitions for example. The difference to a simple TV screen for example, is that these objects are related
to the environment of the screen or display, and that they often are interactive as well.
Many first-person shooter video games simulate the viewpoint of someone using AR systems. In these games the AR
can be used to give visual directions to a location, mark the direction and distance of another person who is not in
line of sight, give information about equipment such as remaining bullets in a gun, and display a myriad of other
images based on whatever the game designers intend. This is also called the head-up display.
In some current applications like in cars or airplanes, this is usually a head-up display integrated into the windshield.
The F-35 Lightning II has no Head-up display. This is because all targets are tracked by the aircraft's situational
awareness and the sensor fusion is presented in the pilot's helmet mounted display. The helmet mounted display
provides an augmented reality system that allows the pilot to look through his own aircraft as if it wasn't there.


History
• 1957-62: Morton Heilig, a cinematographer, creates and patents a simulator called Sensorama with visuals, sound,
vibration, and smell.[5]
• 1966: Ivan Sutherland invents the head-mounted display suggesting it was a window into a virtual world.
• 1975: Myron Krueger creates Videoplace that allows users to interact with virtual objects for the first time.
• 1989: Jaron Lanier coins the phrase Virtual Reality and creates the first commercial business around virtual
worlds.
• 1992: Tom Caudell [6] coins the phrase Augmented Reality while at Boeing helping workers assemble cables
into aircraft.
• 1992: L.B. Rosenberg develops one of the first functioning AR systems, called VIRTUAL FIXTURES, at the
U.S. Air Force Armstrong Labs, and demonstrates benefit on human performance.[7] [8]
• 1992: Steven Feiner, Blair MacIntyre and Doree Seligmann present first major paper on an AR system prototype,
KARMA, at the Graphics Interface conference. Widely cited version of the paper is published in Communications
of the ACM next year.
• 1999: Hirokazu Kato (加藤博一) develops ARToolKit at the HITLab and it is demonstrated at SIGGRAPH that
year.
• 2000: Bruce H. Thomas develops ARQuake, the first outdoor mobile AR game, and is demonstrated in the
International Symposium on Wearable Computers.
• 2008: Wikitude AR Travel Guide [9] launches on Oct. 20, 2008 with the G1 Android phone.
• 2009: Wikitude Drive - AR Navigation System launches on Oct. 28, 2009 for the Android platform.
• 2009: AR Toolkit is ported to Adobe Flash (FLARToolkit) by Saqoosha [10], bringing augmented reality to the
web browser.
• 2010: acrossair [11], AR Browser bringing augmented reality to the mobile user on the iPhone 3Gs for hyper-local
search.

Technology

Hardware
The main hardware components for augmented reality are: display, tracking, input devices, and computer.
Combination of powerful CPU, camera, accelerometers, GPS and solid state compass are often present in modern
smartphones, which make them prospective platforms for augmented reality.

Display
There are three major display techniques for Augmented Reality:
I. Head Mounted Displays
II. Handheld Displays
III. Spatial Displays

Head Mounted Displays
A Head Mounted Display (HMD) places images of both the physical world and registered virtual graphical objects
over the user's view of the world. The HMD's are either optical see-through or video see-through in nature. An
optical see-through display employs half-silver mirror technology to allow views of physical world to pass through
the lens and graphical overlay information to be reflected into the user's eyes. The HMD must be tracked with a six
degree of freedom sensor.This tracking allows for the computing system to register the virtual information to the
physical world. The main advantage of HMD AR is the immersive experience for the user. The graphical
information is slaved to the view of the user. The most common products employed are as follows: MicroVision


Nomad, Sony Glasstron, and I/O Displays.

Handheld Displays
Handheld Augment Reality employs a small computing device with a display that fits in a user's hand. All handheld
AR solutions to date have employed video see-through techniques to overlay the graphical information to the
physical world. Initially handheld AR employed sensors such as digital compasses and GPS units for its six degree
of freedom tracking sensors. This moved onto the use of fiducial marker systems such as the ARToolKit for
tracking. Today vision systems such as SLAM or PTAM are being employed for tracking. Handheld display AR
promises to be the first commercial success for AR technologies. The two main advantages of handheld AR is the
portable nature of handheld devices and ubiquitous nature of camera phones.

Spatial Displays
Instead of the user wearing or carrying the display such as with head mounted displays or handheld devices; Spatial
Augmented Reality (SAR) makes use of digital projectors to display graphical information onto physical objects.
The key difference in SAR is that the display is separated from the users of the system. Because the displays are not
associated with each user, SAR scales naturally up to groups of users, thus allowing for collocated collaboration
between users. SAR has several advantages over traditional head mounted displays and handheld devices. The user
is not required to carry equipment or wear the display over their eyes. This makes spatial AR a good candidate for
collaborative work, as the users can see each other’s faces. A system can be used by multiple people at the same time
without each having to wear a head mounted display. Spatial AR does not suffer from the limited display resolution
of current head mounted displays and portable devices. A projector based display system can simply incorporate
more projectors to expand the display area. Where portable devices have a small window into the world for drawing,
a SAR system can display on any number of surfaces of an indoor setting at once. The tangible nature of SAR makes
this an ideal technology to support design, as SAR supports both a graphical visualisation and passive haptic
sensation for the end users. People are able to touch physical objects, and it is this process that provides the passive
haptic sensation. [2] [12] [13] [14]

Tracking
Modern mobile augmented reality systems use one or more of the following tracking technologies: digital cameras
and/or other optical sensors, accelerometers, GPS, gyroscopes, solid state compasses, RFID, wireless sensors. Each
of these technologies have different levels of accuracy and precision. Most important is the tracking of the pose and
position of the user's head for the augmentation of the user's view. The user's hand(s) can tracked or a handheld input
device could be tracked to provide a 6DOF interaction technique. Stationary systems can employ 6DOF track
systems such as Polhemus, ViCON, A.R.T, or Ascension.

Input devices
This is a current open research question. Some systems, such as the Tinmith system, employ pinch glove techniques.
Another common technique is a wand with a button on it. In case of smartphone, phone itself could be used as 3D
pointing device, with 3D position of the phone restored from the camera images.

Computer
Camera based systems require powerful CPU and considerable amount of RAM for processing camera images.
Wearable computing systems employ a laptop in a backpack configuration. For stationary systems a traditional
workstation with a powerful graphics card. Sound processing hardware could be included in augmented reality
systems.


Software
For consistent merging real-world images from camera and virtual 3D images, virtual images should be attached to
real-world locations in visually realistic way. That means a real world coordinate system, independent from the
camera, should be restored from camera images. That process is called Image registration and is part of Azuma's
definition of Augmented Reality.
Augmented reality image registration uses different methods of computer vision, mostly related to video tracking.
Many computer vision methods of augmented reality are inherited form similar visual odometry methods.
Usually those methods consist of two parts. First interest points, or fiduciary markers, or optical flow detected in the
camera images. First stage can use Feature detection methods like Corner detection, Blob detection, Edge detection
or thresholding and/or other image processing methods.
In the second stage, a real world coordinate system is restored from the data obtained in the first stage. Some
methods assume objects with known 3D geometry(or fiduciary markers) present in the scene and make use of those
data. In some of those cases all of the scene 3D structure should be precalculated beforehand. If not all of the scene is
known beforehand SLAM technique could be used for mapping fiduciary markers/3D models relative positions. If
no assumption about 3D geometry of the scene made structure from motion methods are used. Methods used in the
second stage include projective(epipolar) geometry, bundle adjustment, rotation representation with exponential
map, kalman and particle filters.

Applications

Current applications
Advertising: Marketers started to use AR to promote products via interactive AR applications. For example, at the
2008 LA Auto Show, Nissan unveiled the concept vehicle Cube and presented visitors with a brochure which, when
held against a webcam, showed several versions of the vehicle[15] . In August 2009, Best Buy ran a circular with an
augmented reality code that allowed users with a webcam to interact with the product in 3D.[16]
Support with complex tasks: Complex tasks such as assembly, maintenance, and surgery can be simplified by
inserting additional information into the field of view. For example, labels can be displayed on parts of a system to
clarify operating instructions for a mechanic who is performing maintenance on the system. [17] .AR can include
images of hidden objects, which can be particularly effective for medical diagnostics or surgery. Examples include a
virtual X-ray view based on prior tomography or on real time images from ultrasound or open NMR devices. A
doctor could observe the fetus inside the mother's womb [18] .See also Mixed reality.
Navigation devices: AR can augment the effectiveness of navigation devices for a variety of applications. For
example, building navigation can be enhanced for the purpose of maintaining industrial plants. Outdoor navigation
can be augmented for military operations or disaster management. Head-up displays or personal display glasses in
automobiles can be used to provide navigation hints and traffic information. These types of displays can be useful for
airplane pilots, too. Head-up displays are currently used in fighter jets as one of the first AR applications. These
include full interactivity, including eye pointing.
Industrial Applications: AR can be used to compare the data of digital mock-ups with physical mock-ups for
efficiently finding discrepancys between the two sources. It can further be employed to safeguard digital data in
combination with existing real prototypes, and thus save or minimize the building of real prototypes and improve the
quality of the final product.
Military and emergency services: AR can be applied to military and emergency services as wearable systems to
provide information such as instructions, maps, enemy locations, and fire cells.
Prospecting: In the fields of hydrology, ecology, and geology, AR can be used to display an interactive analysis of
terrain characteristics. Users could use, and collaboratively modify and analyze, interactive three-dimensional maps.


Art: AR can be incorporated into artistic applications that allow artists to create art in real time over reality such as
painting, drawing, modeling, etc. One such example of this phenomenon is called Eyewriter that was developed in
2009 by Zachary Lieberman and a group formed by members of Free Art and Technology (FAT), OpenFrameworks
and the Graffiti Research Lab to help a graffiti artist, who became paralyzed, draw again. [19]
Architecture: AR can be employed to simulate planned construction projects.[20]
Sightseeing: Models may be created to include labels or text related to the objects/places visited. With AR, users can
rebuild ruins, buildings, or even landscapes as they previously existed.[21]
Collaboration: AR can help facilitate collaboration among distributed team members via conferences with real and
virtual participants. The Hand of God is a good example of a collaboration system [22] Also see Mixed reality.
Entertainment and education: AR can be used in the fields of entertainment and education to create virtual objects
in museums and exhibitions, theme park attractions (such as Cadbury World), and games (such as ARQuake and The
Eye of Judgment). Also see Mixed reality.
Music: Pop group Duran Duran included interactive AR projections into their stage show during their 2000 Pop
Trash concert tour.[23] Sydney band Lost Valentinos launched the world's first interactive AR music video on 16
October 2009, where users could print out 5 markers representing a pre-recorded performance from each band
member which they could interact with live and in real-time via their computer webcam and record as their own
unique music video clips to share via YouTube.[24] [25]

Future applications
It is important to note that augmented reality is a costly development in technology. Because of this, the future of AR
is dependent on whether or not those costs can be reduced in some way. If AR technology becomes affordable, it
could be very widespread but for now major industries are the sole buyers that have the opportunity to utilize this
resource.
• Expanding a PC screen into the real environment: program windows and icons appear as virtual devices in real
space and are eye or gesture operated, by gazing or pointing. A single personal display (glasses) could
concurrently simulate a hundred conventional PC screens or application windows all around a user
• Virtual devices of all kinds, e.g. replacement of traditional screens, control panels, and entirely new applications
impossible in "real" hardware, like 3D objects interactively changing their shape and appearance based on the
current task or need.
• Enhanced media applications, like pseudo holographic virtual screens, virtual surround cinema, virtual 'holodecks'
(allowing computer-generated imagery to interact with live entertainers and audience)
• Virtual conferences in "holodeck" style
• Replacement of cellphone and car navigator screens: eye-dialing, insertion of information directly into the
environment, e.g. guiding lines directly on the road, as well as enhancements like "X-ray"-views
• Virtual plants, wallpapers, panoramic views, artwork, decorations, illumination etc., enhancing everyday life. For
example, a virtual window could be displayed on a regular wall showing a live feed of a camera placed on the
exterior of the building, thus allowing the user to effectually toggle a wall's transparency
• With AR systems getting into mass market, we may see virtual window dressings, posters, traffic signs, Christmas
decorations, advertisement towers and more. These may be fully interactive even at a distance, by eye pointing for
example.
• Virtual gadgetry becomes possible. Any physical device currently produced to assist in data-oriented tasks (such
as the clock, radio, PC, arrival/departure board at an airport, stock ticker, PDA, PMP, informational
posters/fliers/billboards, in-car navigation systems, etc.) could be replaced by virtual devices that cost nothing to
produce aside from the cost of writing the software. Examples might be a virtual wall clock, a to-do list for the
day docked by your bed for you to look at first thing in the morning, etc.


• Subscribable group-specific AR feeds. For example, a manager on a construction site could create and dock
instructions including diagrams in specific locations on the site. The workers could refer to this feed of AR items
as they work. Another example could be patrons at a public event subscribing to a feed of direction and
information oriented AR items.
• AR systems can help the visually impaired navigate in a much better manner (combined with a text-to-speech
software).

Notable researchers
• Steven Feiner, Professor at Columbia University, is a leading pioneer of augmented reality, and author of the first
paper on an AR system prototype, KARMA (the Knowledge-based Augmented Reality Maintenance Assistant),
along with Blair MacIntyre and Doree Seligmann.[26]
• L.B. Rosenberg developed one of the first known AR systems, called Virtual Fixtures, while working at the U.S.
Air Force Armstrong Labs in 1991, and published first study of how an AR system can enhance human
performance.[7] [8]
• Mark Billinghurst and Daniel Wagner jump started the field of AR on mobile phones. They developed the first
marker tracking systems for mobile phones and PDAs.[27]
• Bruce H. Thomas and Wayne Piekarski develop the Tinmith system in 1998. They along with Steve Feiner with
his MARS system pioneer outdoor augmented reality.

Conferences
• 1st International Workshop on Augmented Reality, IWAR'98, San Francisco, Nov. 1998.
• 2nd International Workshop on Augmented Reality (IWAR'99 [28]), San Francisco, Oct. 1999.
• 1st International Symposium on Mixed Reality (ISMR'99), Yokohama, Japan, March 1999.
• 2nd International Symposium on Mixed Reality (ISMR'01), Yokohama, Japan, March 2001.
• 1st International Symposium on Augmented Reality (ISAR 2000 [29]), Munich, Oct. 2000.
• 2nd International Symposium on Augmented Reality (ISAR 2001 [30]), New York, Oct. 2001.
• 1st International Symposium on Mixed and Augmented Reality (ISMAR 2002 [31]), Darmstadt, Oct. 2002.
• 2nd International Symposium on Mixed and Augmented Reality (ISMAR 2003 [32]), Tokyo, Oct. 2003.
• 3rd International Symposium on Mixed and Augmented Reality (ISMAR 2004 [33]), Arlington, VA, Nov. 2004.
• 4th International Symposium on Mixed and Augmented Reality (ISMAR 2005 [34]), Vienna, Oct. 2005.
• 5th International Symposium on Mixed and Augmented Reality (ISMAR 2006 [35]) Santa Barbara, Oct. 2006.
• 6th International Symposium on Mixed and Augmented Reality (ISMAR 2007 [36]) Nara, Japan, Nov. 2007.
• 7th International Symposium on Mixed and Augmented Reality (ISMAR 2008 [37]) Cambridge, United Kingdom,
Sep. 2008.
• 8th International Symposium on Mixed and Augmented Reality (ISMAR 2009 [38]) Orlando, Oct. 2009.
• Augmented Reality Developer Camp (AR DevCamp [39]) in Mountain View, Dec. 2009.


Software

Free software
• ARToolKit is a Cross-platform Library for the creation of augmented reality applications, developed by Hirokazu
Kato in 1999 [40] and was released by the University of Washington HIT Lab. Currently it is maintained as an
opensource project hosted on SourceForge [41] with commercial licenses available from ARToolWorks[42] .
• ATOMIC Authoring Tool is a Cross-platform Authoring Tool software, for Augmented Reality Applications,
which is a Front end for the ARToolKit library. Was developed for non-programmers, to create small and simple,
Augmented Reality applications, released under the GNU GPL License.
• ATOMIC Web Authoring Tool Is a children project from: ATOMIC Authoring Tool that enables the creation of
Augmented Reality applications and export it, to any website. Developed as A front end (Graphic Interface) for
the Flartoolkit library. And it's licensed under the GNU GPL License.
• OSGART [43] - a combination of ARToolKit and OpenSceneGraph
• ARToolKitPlus [44] - extended version of ARToolKit, only targeted to handheld users and developers of
AR-oriented software. No longer developed.
• Mixed Reality Toolkit (MRT) [45] - University College London
• FLARToolKit [46] - an ActionScript 3 port of ARToolKit for Flash 9+.
• SLARToolkit [47] - a Silverlight port of NyARToolkit.
• NyARToolkit [48] - an ARToolkit class library released for virtual machines, particularly those which host Java, C#
and Android.
• ARDesktop [49] - ARToolKit class library that creates a three-dimensional desktop interface with controls and
widgets.
• AndAR [50] - A native port of ARToolkit to the Android platform.
• mixare [51] - Open-Source (GPLv3) Augmented Reality Engine for Android. It works as a completely autonomous
application and is available as well for the development of own implementations.
• OpenMAR [52] - Open Mobile Augmented Reality component framework for the Symbian platform, released
under EPL

Non-commercial use
• PTAM [53]
• ARTag [54]

Books
• Woodrow Barfield, and Thomas Caudell, eds. Fundamentals of Wearable Computers and Augmented Reality.
Mahwah, NJ: Lawrence Erlbaum, 2001. ISBN 0805829016.
• Oliver Bimber and Ramesh Raskar. Spatial Augmented Reality: Merging Real and Virtual Worlds. A K Peters,
2005. ISBN 1568812302.
• Michael Haller, Mark Billinghurst and Bruce H. Thomas. Emerging Technologies of Augmented Reality:
Interfaces and Design. Idea Group Publishing, 2006. ISBN 1599040662 , publisher listing [55]
• Rolf R. Hainich. "The end of Hardware : A Novel Approach to Augmented Reality" [56] 2nd ed.: Booksurge, 2006.
ISBN 1419652184. 3rd ed. ("Augmented Reality and Beyond"): Booksurge, 2009, ISBN 1-4392-3602-X.
• Stephen Cawood and Mark Fiala. Augmented Reality: A Practical Guide, 2008, ISBN 1934356034


In popular culture

Television & film
• The television series Dennō Coil depicts a near-future where children use AR glasses to enhance their
environment with games and virtual pets.
• The television series Firefly depicts numerous AR applications, including a real-time medical scanner which
allows a doctor to use his hands to manipulate a detailed and labeled projection of a patient's brain.
• In the 1993 ABC miniseries Wild Palms, a Scientology-like organization used holographic projectors to overlay
virtual reality images over physical reality.
• In the movie Iron Man, Tony Stark (Robert Downey Jr.) uses an augmented reality system to design his
super-powered suit.
• In the video game Heavy Rain, Norman Jayden, an FBI profiler, possesses a set of experimental augmented
reality glasses called an "Added Reality Interface", or ARI. It allows him to rapidly investigate crime scenes and
analyze evidence.
• In the Philippines, during their first automated elections (2010), ABS-CBN Broadcasting Corporation used
augmented reality during the counting of votes for all National and Local Candidates and in delivering news
reports.

Literature
• The table top role-playing game, Shadowrun, introduced AR into its game world. Most of the characters in the
game use viewing devices to interact with the AR world most of the time.
• Cybergeneration, a table top role-playing game by R. Talsorian, includes "virtuality", an augmented reality
created through v-trodes, cheap, widely available devices people wear at their temples.
• The books Halting State by Charles Stross and Rainbows End by Vernor Vinge include augmented reality
primarily in the form of virtual overlays over the real world. Halting State mentions Copspace, which is used by
cops, and the use by gamers to overlay their characters onto themselves during a gaming convention. Rainbows
End mentions outdoor overlays based on popular fictional universes from H. P. Lovecraft and Terry Pratchett
among others.
• The term "Geohacking" has been coined by William Gibson in his book Spook Country, where artists use a
combination of GPS and 3D graphics technology to embed rendered meshes in real world landscapes.
• In The Risen Empire, by Scott Westerfeld, most - if not all - people have their own "synesthesia". An AR menu
unique to the user that is projected in front of them, but they can only see their own synesthesia menus. It is
controlled by hand gestures, blink patterns, where the user is looking, clicks of the tongue, etc.
• In the Greg Egan novel Distress, the 'Witness' software used to record sights and sounds experienced by the user
can be set-up to scan what the user is seeing and highlight people the user is looking out for.
• In the Revelation Space series of novels, Alastair Reynolds characters frequently employ "Entoptics" which are
essentially a highly developed form of augmented reality, going so far as to entirely substitute natural perception.


See also
• Alternate reality game
• ARQuake
• Augmented browsing
• Augmented virtuality
• Bionic contact lens
• Camera resectioning
• Computer-mediated reality
• Cyborg
• Head-mounted display
• Mixed reality
• Mediated reality
• Simulated reality
• Virtual retinal display
• Virtuality Continuum
• Virtual reality
• Wearable computer

External links
• Media related to Augmented Reality at Wikimedia Commons

References
[1] The interactive system is no longer a precise location, but the whole environment; interaction is no longer simply a face-to-screen exchange,
but dissolves itself in the surrounding space and objects. Using an information system is no longer exclusively a conscious and intentional act.

Brian X. Chen (2009-08-25). "If You’re Not Seeing Data, You’re Not Seeing" (http:/ / www. wired. com/ gadgetlab/
tag/augmented-reality/). Wired Magazine. . Retrieved 2009-08-26.
[2] R. Azuma, A Survey of Augmented Reality (http:/ / www. cs. unc. edu/ ~azuma/ ARpresence. pdf) Presence: Teleoperators and Virtual
Environments, pp. 355–385, August 1997.
[3] P. Milgram and A. F. Kishino, Taxonomy of Mixed Reality Visual Displays (http:/ / vered. rose. utoronto. ca/ people/ paul_dir/ IEICE94/ ieice.
html) IEICE Transactions on Information and Systems, E77-D(12), pp. 1321-1329, 1994.
[4] Mediated Reality with implementations for everyday life (http:/ / wearcam. org/ presence_connect/ ), 2002 August 6th, Presence Connect, the
on line companion to the MIT Press journal PRESENCE: Teleoperators and Virtual Environments, MIT Press
[5] http:/ / www. google. com/ patents?q=3050870
[6] http:/ / www. ece. unm. edu/ morenews/ profile_caudell. html
[7] L. B. Rosenberg. The Use of Virtual Fixtures As Perceptual Overlays to Enhance Operator Performance in Remote Environments. Technical
Report AL-TR-0089, USAF Armstrong Laboratory, Wright-Patterson AFB OH, 1992.
[8] L. B. Rosenberg, "The Use of Virtual Fixtures to Enhance Operator Performance in Telepresence Environments" SPIE Telemanipulator
Technology, 1993.
[9] http:/ / www. youtube. com/ watch?v=8EA8xlicmT8
[10] http:/ / saqoosha. net/ en/ flartoolkit/ start-up-guide/
[11] http:/ / www. youtube. com/ watch?v=o_mUFS992Cw
[12] Ramesh Raskar, Spatially Augmented Reality (http:/ / www. cs. unc. edu/ ~raskar/ Office), First International Workshop on Augmented
Reality, Sept 1998
[13] David Drascic of the University of Toronto is a developer of ARGOS: A Display System for Augmenting Reality (http:/ / vered. rose.
utoronto. ca/ people/ david_dir/ CHI93/ CHI93. full. html). David also has a number of AR related papers on line, accessible from his home
page (http:/ / vered. rose. utoronto. ca/ people/ David. html).
[14] Augmented reality brings maps to life (http:/ / www. newscientist. com/ article/ dn7695) July 19, 2005
[15] company website (http:/ / www. nissanusa. com/ cube/ )
[16] Best Buy goes 3D, even augmented reality isn't safe from advertising (http:/ / www. engadget. com/ 2009/ 08/ 06/
best-buy-goes-3d-even-augmented-reality-isnt-safe-from-adverti/ )


[17] "ARMAR:Augmented Reality for Maintenance and Repair (ARMAR)" (http:/ / graphics. cs. columbia. edu/ projects/ armar/ index. htm). .
Retrieved 2010-01-06.
[18] "UNC Ultrasound/Medical Augmented Reality Research" (http:/ / www. cs. unc. edu/ Research/ us/ ). . Retrieved 2010-01-06.
[19] "THE EYEWRITER" (http:/ / www. eyewriter. org/ ). . Retrieved 2010-04-27.
[20] "AUGMENTED REALITY : AN APPLICATION FOR ARCHITECTURE" (http:/ / www. usc. edu/ dept/ architecture/ mbs/ thesis/ anish/ ).
. Retrieved 2010-01-06.
[21] "Archeoguide: System Architecture of a Mobile Outdoor Augmented Reality System" (http:/ / portal. acm. org/ citation. cfm?id=854948). .
[22] "Hand of God" (http:/ / www. hog3d. net/ ). . Retrieved 2009-12-18.
[23] Pair, J., Wilson, J., Chastine, J., Gandy, M. " The Duran Duran Project: The Augmented Reality Toolkit in Live Performance (http:/ /
ieeexplore. ieee. org/ xpl/ freeabs_all. jsp?tp=& arnumber=1107010)". The First IEEE International Augmented Reality Toolkit Workshop,
2002. ( photos and video (http:/ / www. jarrellpair. com/ ddar/ index. html))
[24] Gizmodo: Sydney Band Uses Augmented Reality For Video Clip (http:/ / www. gizmodo. com. au/ 2009/ 10/
sydney-band-uses-augmented-reality-for-video-clip/ )
[25] cnet: Augmented reality in Aussie film clip (http:/ / www. cnet. com. au/ augmented-reality-in-aussie-film-clip-339299097. htm)
[26] "Knowledge-based augmented reality" (http:/ / portal. acm. org/ citation. cfm?id=159587). ACM. July, 1993. .
[27] Wagner, Daniel (September 29, 2009). "First Steps Towards Handheld Augmented Reality" (http:/ / portal. acm. org/ citation.
cfm?id=946910). ACM. . Retrieved 2009-09-29.
[28] http:/ / ieeexplore. ieee. org/ xpl/ tocresult. jsp?isNumber=17413
[33] http:/ / ieeexplore. ieee. org/ xpl/ tocresult. jsp?isnumber=30137
[34] http:/ / ieeexplore. ieee. org/ xpl/ tocresult. jsp?isnumber=32972
[35] http:/ / www. ismar06. org
[36] http:/ / www. ismar07. org/
[37] http:/ / ismar08. org/ wiki/ doku. php
[38] http:/ / www. ismar09. org
[39] http:/ / www. ardevcamp. org
[40] Kato, H., Billinghurst, M. "Marker tracking and hmd calibration for a video-based augmented reality conferencing system.",In Proceedings
of the 2nd IEEE and ACM International Workshop on Augmented Reality (IWAR 99), October 1999.
[41] ARToolKit SourceForge page (http:/ / sourceforge. net/ projects/ artoolkit)
[42] ARToolWorks company website (http:/ / www. artoolworks. com)
[43] http:/ / www. osgart. org/ wiki/ Main_Page
[44] http:/ / studierstube. org/ handheld_ar/ artoolkitplus. php
[45] http:/ / www. cs. ucl. ac. uk/ staff/ r. freeman/
[46] http:/ / www. libspark. org/ wiki/ saqoosha/ FLARToolKit/ en
[47] http:/ / slartoolkit. codeplex. com
[48] http:/ / nyatla. jp/ nyartoolkit/ wiki/ index. php?FrontPage. en
[49] http:/ / wiki. livedoor. jp/ wah_wah_hawah/
[50] http:/ / code. google. com/ p/ andar/
[51] http:/ / www. mixare. org/
[52] http:/ / OpenMAR. org
[53] http:/ / www. robots. ox. ac. uk/ ~gk/ PTAM/
[54] http:/ / www. artag. net/
[55] http:/ / www. igi-pub. com/ books/ details. asp?id=6456
[56] http:/ / www. theendofhardware. org

Face detection 37

Face detection
Face detection is a computer technology that determines the locations and sizes of human faces in arbitrary
(digital) images. It detects facial features and ignores anything else, such as buildings, trees and bodies.

Definition and relation to other tasks
Face detection can be regarded as a specific case of object-class detection; In object-class detection, the task is to
find the locations and sizes of all objects in an image that belong to a given class. Examples include upper torsos,
pedestrians, and cars.
Face detection can be regarded as a more general case of face localization; In face localization, the task is to find the
locations and sizes of a known number of faces (usually one). In face detection, one does not have this additional
information.
Early face-detection algorithms focused on the detection of frontal human faces, whereas newer algorithms attempt
to solve the more general and difficult problem of multi-view face detection. That is, the detection of faces that are
either rotated along the axis from the face to the observer (in-plane rotation), or rotated along the vertical or left-right
axis (out-of-plane rotation),or both.

Techniques
Face detection as a pattern-classification task
Many algorithms implement the face-detection task as a binary pattern-classification task. That is, the content of a
given part of an image is transformed into features, after which a classifier trained on example faces decides whether
that particular region of the image is a face, or not.
Often, a window-sliding technique is employed. That is, the classifier is used to classify the (usually square or
rectangular) portions of an image, at all locations and scales, as either faces or non-faces (background pattern).
Controlled background
Images with a plain or a static background are easy to process. Remove the background and only the faces will be
left, assuming the image only contains a frontal face.
By color
Using skin color to find face segments is a vulnerable technique. The database may not contain all the skin colors
possible. Lighting can also affect the results. Non-animate objects with the same color as skin can be picked up since
the technique uses color segmentation. The advantages are the lack of restriction to orientation or size of faces and a
good algorithm can handle complex backgrounds[1] .
By motion
Faces are usually moving in real-time videos. Calculating the moving area will get the face segment. However, other
objects in the video can also be moving and would affect the results. A specific type of motion on faces is blinking.
Detecting a blinking pattern in an image sequence can detect the presence of a face[2] . Eyes usually blink together
and symmetrically positioned, which eliminates similar motions in the video. Each image is subtracted from the
previous image. The difference image will show boundaries of moved pixels. If the eyes happen to be blinking, there
will be a small boundary within the face.
Model-based
A face model can contain the appearance, shape, and motion of faces. There are several shapes of faces. Some
common ones are oval, rectangle, round, square, heart, and triangle. Motions include, but not limited to, blinking,
raised eyebrows, flared nostrils, wrinkled forehead, and opened mouth. The face models will not be able to represent

Face detection 38

any person making any expression, but the technique does result in an acceptable degree of accuracy[3] . The models
are passed over the image to find faces, however this technique works better with face tracking. Once the face is
detected, the model is laid over the face and the system is able to track face movements.

Applications
Face detection is used in biometrics, often as a part of (or together with) a facial recognition system. It is also used in
video surveillance, human computer interface and image database management. Some recent digital cameras use
face detection for autofocus[4] . Also, face detection is useful for selecting regions of interest in photo slideshows that
use a pan-and-scale Ken Burns effect so
Face detection is gaining the interest of marketers. A webcam can be integrated into a television and detect any face
that walks by. The system then calculates the race, gender, and age range of the face. Once the information is
collected, a series of advertisements can be played that is specific toward the detected race/gender/age.

Popular algorithms
• Viola-Jones object detection framework - Viola & Jones [5] (2001)
• Schneiderman & Kanade [6] (2000)
• Rowley, Baluja & Kanade: Neural Network-based Face Detection [7] (1998)

See also
• TSL color space
• Computer vision
• Facial recognition system
• Three-dimensional face recognition
• iPhoto
• Picasa

External links
• Detecting faces in images: a survey [8]
• Open source J2ME code for face detection using a cellphone camera [9]
• Open source Computer Vision library that includes face detection [10]
• Face detection techniques [11]

References
[1] (http:/ / w3. ualg. pt/ ~ftomaz/ fr/ fr. php/ ) Face detection and recognition: color segmentation
[2] (http:/ / www-prima. imag. fr/ ECVNet/ IRS95/ node13. html) Blink detection
[3] (http:/ / www. cs. rutgers. edu/ ~decarlo/ facetrack. html) Model-based face tracking
[4] (http:/ / www. dcresource. com/ reviews/ canon/ powershot_s5-review/ index. shtml) Canon Powershot S5IS review
[5] http:/ / www. merl. com/ reports/ docs/ TR2004-043. pdf
[6] http:/ / www. robots. ox. ac. uk/ ~cvrg/ trinity2003/ schneiderman_cvpr00. pdf
[7] http:/ / www. ri. cmu. edu/ pub_files/ pub1/ rowley_henry_1998_1/ rowley_henry_1998_1. pdf
[8] http:/ / vision. ai. uiuc. edu/ mhyang/ face-detection-survey. html
[9] http:/ / code. google. com/ p/ jjil/
[10] http:/ / sourceforge. net/ projects/ opencvlibrary/
[11] http:/ / www. facedetection. com/ facedetection/ techniques. htm/


Feature detection (computer vision)
Feature detection

Output of a typical corner detection algorithm
Edge detection

Canny

Canny-Deriche

Differential

Sobel

Roberts Cross

Interest point detection

Corner detection

Harris operator

Shi and Tomasi

Level curve curvature

SUSAN

FAST

Blob detection

Laplacian of Gaussian (LoG)

Difference of Gaussians (DoG)

Determinant of Hessian (DoH)

Maximally stable extremal regions

PCBR

Hough transform

Ridge detection

Affine invariant feature detection

Affine shape adaptation

Harris affine

Hessian affine

Feature description

SIFT

SURF

GLOH


LESH

Scale-space

Scale-space axioms

Implementation details

Pyramids

In computer vision and image processing the concept of feature detection refers to methods that aim at computing
abstractions of image information and making local decisions at every image point whether there is an image feature
of a given type at that point or not. The resulting features will be subsets of the image domain, often in the form of
isolated points, continuous curves or connected regions.

Definition of a feature
There is no universal or exact definition of what constitutes a feature, and the exact definition often depends on the
problem or the type of application. Given that, a feature is defined as an "interesting" part of an image, and features
are used as a starting point for many computer vision algorithms. Since features are used as the starting point and
main primitives for subsequent algorithms, the overall algorithm will often only be as good as its feature detector.
Consequently, the desirable property for a feature detector is repeatability: whether or not the same feature will be
detected in two or more different images of the same scene.
Feature detection is a low-level image processing operation. That is, it is usually performed as the first operation on
an image, and examines every pixel to see if there is a feature present at that pixel. If this is part of a larger
algorithm, then the algorithm will typically only examine the image in the region of the features. As a built-in
pre-requisite to feature detection, the input image is usually smoothed by a Gaussian kernel in a scale-space
representation and one or several feature images are computed, often expressed in terms of local derivative
operations.
Occasionally, when feature detection is computationally expensive and there are time constraints, a higher level
algorithm may be used to guide the feature detection stage, so that only certain parts of the image are searched for
features.
Where many computer vision algorithms use feature detection as the initial step, so as a result, a very large number
of feature detectors have been developed. These vary widely in the kinds of feature detected, the computational
complexity and the repeatability. At an overview level, these feature detectors can (with some overlap) be divided
into the following groups:

Types of image features

Edges
Edges are points where there is a boundary (or an edge) between two image regions. In general, an edge can be of
almost arbitrary shape, and may include junctions. In practice, edges are usually defined as sets of points in the
image which have a strong gradient magnitude. Furthermore, some common algorithms will then chain high gradient
points together to form a more complete description of an edge. These algorithms usually place some constraints on
the properties of an edge, such as shape, smoothness, and gradient value.
Locally, edges have a one dimensional structure.


Corners / interest points
The terms corners and interest points are used somewhat interchangeably and refer to point-like features in an image,
which have a local two dimensional structure. The name "Corner" arose since early algorithms first performed edge
detection, and then analysed the edges to find rapid changes in direction (corners). These algorithms were then
developed so that explicit edge detection was no longer required, for instance by looking for high levels of curvature
in the image gradient. It was then noticed that the so-called corners were also being detected on parts of the image
which were not corners in the traditional sense (for instance a small bright spot on a dark background may be
detected). These points are frequently known as interest points, but the term "corner" is used by tradition.

Blobs / regions of interest or interest points
Blobs provide a complementary description of image structures in terms of regions, as opposed to corners that are
more point-like. Nevertheless, blob descriptors often contain a preferred point (a local maximum of an operator
response or a center of gravity) which means that many blob detectors may also be regarded as interest point
operators. Blob detectors can detect areas in an image which are too smooth to be detected by a corner detector.
Consider shrinking an image and then performing corner detection. The detector will respond to points which are
sharp in the shrunk image, but may be smooth in the original image. It is at this point that the difference between a
corner detector and a blob detector becomes somewhat vague. To a large extent, this distinction can be remedied by
including an appropriate notion of scale. Nevertheless, due to their response properties to different types of image
structures at different scales, the LoG and DoH blob detectors are also mentioned in the article on corner detection.

Ridges
For elongated objects, the notion of ridges is a natural tool. A ridge descriptor computed from a grey-level image can
be seen as a generalization of a medial axis. From a practical viewpoint, a ridge can be thought of as a
one-dimensional curve that represents an axis of symmetry, and in addition has an attribute of local ridge width
associated with each ridge point. Unfortunately, however, it is algorithmically harder to extract ridge features from
general classes of grey-level images than edge-, corner- or blob features. Nevertheless, ridge descriptors are
frequently used for road extraction in aerial images and for extracting blood vessels in medical images -- see ridge
detection.

Feature detectors

Common feature detectors and their classification:
Feature detector Edge Corner Blob

Canny X

Sobel X

Harris & Stephens / Plessey X X

SUSAN X X

Shi & Tomasi X

Level curve curvature X

FAST X

Laplacian of Gaussian X X

Difference of Gaussians X X

Determinant of Hessian X X


MSER X

PCBR X

Grey-level blobs X

Feature extraction
Once features have been detected, a local image patch around the feature can be extracted. This extraction may
involve quite considerable amounts of image processing. The result is known as a feature descriptor or feature
vector. Among the approaches that are used to feature description, one can mention N-jets and local histograms (see
scale-invariant feature transform for one example of a local histogram descriptor). In addition to such attribute
information, the feature detection step by itself may also provide complementary attributes, such as the edge
orientation and gradient magnitude in edge detection and the polarity and the strength of the blob in blob detection.

References
• T. Lindeberg (2008/2009). "Scale-space" [1]. Encyclopedia of Computer Science and Engineering (Benjamin
Wah, ed), John Wiley and Sons IV: 2495--2504. doi:10.1002/9780470050118.ecse609. (summary and review of a
number of feature detectors formulated based on a scale-space operations)
• Canny, J. (1986). "A Computational Approach To Edge Detection". IEEE Trans. Pattern Analysis and Machine
Intelligence 8: 679–714. doi:10.1109/TPAMI.1986.4767851.. (Canny edge detection)
• C. Harris and M. Stephens (1988). "A combined corner and edge detector" [2] (PDF). Proceedings of the 4th Alvey
Vision Conference [2]. pp. pages 147--151.(Harris/Plessey corner detection)
• S. M. Smith and J. M. Brady (May 1997). "SUSAN - a new approach to low level image processing" [3].
International Journal of Computer Vision 23 (1): 45–78. doi:10.1023/A:1007963824710.(The SUSAN corner
detector)
• J. Shi and C. Tomasi (June 1994). "Good Features to Track," [4]. 9th IEEE Conference on Computer Vision and
Pattern Recognition [4]. Springer.(The Shi and Tomasi corner detector)
• M. Trajkovic and M. Hedley (1998). "Fast corner detection". Image and Vision Computing 16 (2): 75–87.
doi:10.1016/S0262-8856(97)00056-5.(The FAST corner detector)
• T. Lindeberg (1998). "Feature detection with automatic scale selection" [5] (abstract). International Journal of
Computer Vision 30 (2): pp 77--116.(Laplacian and determinant of Hessian blob detection as well as automatic
scale selection)
• D. Lowe (2004). "Distinctive Image Features from Scale-Invariant Keypoints" [6]. International Journal of
Computer Vision 60: 91. doi:10.1023/B:VISI.0000029664.99615.94.(DOG blob detection with automatic scale
selection)
• J. Matas, O. Chum, M. Urban and T. Pajdla (2002). "Robust wide baseline stereo from maximally stable
extremum regions" [7] (PDF). British Machine Vision Conference [7]. pp. 384–393.(The MSER blob detector)
• T. Lindeberg (1993). "Detecting Salient Blob-Like Image Structures and Their Scales with a Scale-Space Primal
Sketch: A Method for Focus-of-Attention" [8] (abstract). International Journal of Computer Vision 11 (3): pp
283--318. doi:10.1007/BF01469346.(Grey-level blob detection and scale-space blobs)
• R. Haralick, "Ridges and Valleys on Digital Images," Computer Vision, Graphics, and Image Processing vol. 22,
no. 10, pp. 28-38, Apr. 1983. (Ridge detection using facet model)
• J. L. Crowley and A. C. Parker, "A Representation for Shape Based on Peaks and Ridges in the Difference of
Low Pass Transform", IEEE Transactions on PAMI, PAMI 6 (2), pp 156-170, March 1984. (Ridge detection
based on DOGs)
• D. Eberly , R. Gardner , B. Morse , S. Pizer , C. Scharlach, Ridges for image analysis, Journal of Mathematical
Imaging and Vision, v.4 n.4, p.353-373, Dec. 1994. (Fixed scale ridge detection)


• T. Lindeberg (1998). "Edge detection and ridge detection with automatic scale selection" [9] (abstract).
International Journal of Computer Vision 30 (2): pp 117--154. doi:10.1023/A:1008097225773.(Ridge detection
with automatic scale selection)

See also
• Edge detection
• Corner detection
• Blob detection
• Ridge detection
• Interest point detection
• Scale-space
• Feature detection
• Feature extraction
• Feature (Computer vision)
• Computer vision

References
[1] http:/ / www. nada. kth. se/ ~tony/ abstracts/ Lin08-EncCompSci. html
[2] http:/ / www. csse. uwa. edu. au/ ~pk/ research/ matlabfns/ Spatial/ Docs/ Harris/ A_Combined_Corner_and_Edge_Detector. pdf
[3] http:/ / citeseer. ist. psu. edu/ smith95susan. html
[4] http:/ / citeseer. ist. psu. edu/ shi94good. html
[5] http:/ / www. nada. kth. se/ cvap/ abstracts/ cvap198. html
[6] http:/ / citeseer. ist. psu. edu/ 654168. html
[7] http:/ / cmp. felk. cvut. cz/ ~matas/ papers/ matas-bmvc02. pdf
[8] http:/ / www. nada. kth. se/ ~tony/ abstracts/ Lin92-IJCV. html
[9] http:/ / www. nada. kth. se/ cvap/ abstracts/ cvap191. html


Lane departure warning system
In road-transport terminology, a lane departure warning system is a
mechanism designed to warn a driver when the vehicle begins to move
out of its lane (unless a turn signal is on in that direction) on freeways
and arterial roads. These systems are designed to minimize accidents
by addressing the main causes of collisions: driving error, distraction
and drowsiness. In 2009 the NHTSA began studying whether to
mandate lane departure warning systems and frontal collision warning
systems on automobiles.[1]

There are two main types of systems: Roadway with lane markings
• systems which warn the driver if the vehicle is leaving its lane.
(visual, audible, and/or vibration warnings)
• systems which warn the driver and if no action is taken automatically take steps to ensure the vehicle stays in its
lane.
The first production lane departure warning system in Europe was developed by the United States's Iteris company
for Mercedes Actros commercial trucks. The system debuted in 2000 and is now available on most trucks sold in
Europe. In 2002, the Iteris system became available on Freightliner Trucks' trucks in North America. In all of these
systems, the driver is warned of unintentional lane departures by an audible rumble strip sound generated on the side
of the vehicle drifting out of the lane. If a turn signal is used, no warnings are generated.

Timeline
2001: Nissan Motors began offering a Lane Keeping Support system on the Cima sold in Japan.[2] In 2004, the first
passenger vehicle system available in North America was jointly developed by Iteris and Valeo for Nissan on the
Infiniti FX and in 2005 the M vehicles.[3] In this system, a camera mounted in the overhead console above the mirror
monitors the lane markings on a roadway. A warning tone is triggered when the vehicle begins to drift over the
marking to alert the driver. In 2007 Infiniti offered a newer version of this feature, which it calls the Lane Departure
Prevention (LDP) system. This feature utilizes the vehicle stability control system to help assist the driver maintain
lane position by applying gentle brake pressure to the appropriate wheels.[4]
2002: Toyota introduced its Lane Monitoring System[5] on vehicles such as the Cardina[6] and Alphard sold in Japan,
this system warns the driver if it appears the vehicle is beginning to drift out of its lane.[7] In 2004, Toyota added a
Lane Keeping Assist feature to the Crown Majesta which can apply a small-counter steering force to aid in keeping
the vehicle in its lane.[8] In 2006, Lexus introduced a multi-mode Lane Keeping Assist system on the LS 460 which
utilizes stereo cameras along with more sophisticated object and pattern recognition processors, this system can issue
an audiovisual warning and also using the Electric Power Steering (EPS) steer the vehicle to hold its lane, this
system also applies counter-steering torque to help ensure the driver does not over-correct or "saw" the steering
wheel while attempting to return the vehicle to its proper lane,[9] if the radar cruise control system is engaged the
Lane Keep function works to help reduce the driver's steering input burden by providing steering torque, however
the driver must remain active otherwise the system will deactivate.[10] (see a demonstration on YouTube [11])
2003: Honda launched their Lane Keep Assist System (LKAS) on the Inspire.[12] [13] It provides up to 80% of
steering torque to keep the car in its lane on the highway. It is also designed to make highway driving less
cumbersome by minimizing the driver's steering input.[14] A camera is mounted at the top of the windshield, just
above the rear-view mirror scans the road ahead in a 40-degree radius, picking up the dotted white lines used to
divide lane boundaries on the highway. The computer recognizes that you're locked into a particular lane, monitors
how sharp the curve is and uses factors such as yaw and vehicle speed to calculate what steering input is required.[15]


2005: Citroën became first in Europe to offer LDWS on their 2005 C4 and C5 models, and now also on their C6.
This system uses infrared sensors to monitor lane markings on the road surface. A vibration mechanism in the seat
alerts the driver of deviations.[16] Audi began in 2007 offering its Audi Lane Assist feature[17] for the first time on
the Q7. This system unlike the Japanese "assist" systems will not intervene in the actual driving rather vibrate the
steering wheel if the vehicle appears to be exiting its lane. The LDW System in Audi is based on a forward-looking
video-camera in visible range as opposed to the downward-looking infrared sensors in Citroën.[18]
2007: General Motors introduced Lane Departure Warning on its 2008 model year Cadillac STS, DTS and Buick
Lucerne models. The General Motors system warns the driver, with an audible tone and a warning indicator in the
dashboard. BMW also introduced Lane Departure Warning on the 5 series and 6 series using a vibrating steering
wheel to warn the driver of unintended departures. Volvo introduced the Lane Departure Warning system along with
the Driver Alert Control on its 2008 model year S80 and on the new V70 and XC70 executive cars. Volvo's lane
departure warning system uses a camera to track road markings and sound an alarm when drivers depart their lane
without signaling. The systems used by BMW, Volvo, and General Motors are based on core technology from
Mobileye
2009: Mercedes-Benz began offering a Lane Keeping Assist function on the new E-class.[19] This system warns the
driver with a vibrating steering wheel if it appears the vehicle is beginning to leave its lane. And a new feature will
automatically deactivate and reactivate if it ascertains the driver is intentionally leaving his lane, for instance if the
driver is aggressively cornering. However this system will not automatically correct the vehicle to ensure it stays in
its lane like the Japanese "assist" systems.
2010: Kia Motors offers the 2011 Cadenza premium sedan with an optional Lane Departure Warning System
(LDWS) in select markets. This system uses a flashing dashboard telltale and emits an audible warning when a white
lane marking is being crossed, and emits a louder audible warning when a yellow line marking is crossed. This
system is canceled when a turn signal is operating, or by pressing a deactivation switch on the dashboard. The
system works by using an optical sensor on both sides of the car.
FIAT is also launching its Lane Keep Assist feature based on TRW lane detect system. Peugeot introduced the same
system than Citroën in its new 308.
Lane departure warning systems are now combining prevention with risk reports in the transportation industry.
Viewnyx applies video based technologies to assist fleets in lowering their driving liability costs. By providing
Safety Managers with driver and fleet risk assessment reports and tools to facilitate proactive coaching & training to
eliminate high risk behaviors. The Lookout solution is currently being used by North American fleets. There are first
solutions for implementing a lane departure warning system on a mobile phone.[20]

See also
• Precrash system
• Adaptive cruise control
• Blind spot monitor
• Intelligent car
• Advanced front lighting (swiveling headlamps)
• Lane


External links
• Intelligent Vehicle News and Information [21]

References
[1] http:/ / www. detnews. com/ article/ 20090702/ AUTO01/ 907020346/ 1148/ auto01/ NHTSA+ may+ impose+ more+ safety+ features
[2] Nissan Demos New Lane Keeping Products (02/01) (http:/ / ivsource. net/ archivep/ 2001/ feb/ 010212_nissandemo. html)
[3] Valeo (2004-03-31). "Valeo’s revolutionary Lane Departure Warning System makes debut on Nissan Infiniti vehicles" (http:/ / www. valeo.
com/ automotive-supplier/ webdav/ site/ valeo/ shared/ en/ pdf/ 4presse/ communiques/ 2004/ ldws_uk. pdf). Press release. .
[4] Nissan (2007-07-28). "The 2008 Infiniti Lineup - Charting the Changes" (http:/ / www. nissannews. com/ infiniti/ news/ products/
20070628101227. shtml). Press release. .
[5] http:/ / www. toyota. co. jp/ en/ tech/ its/ vision/ history. html
[6] Toyota Cardina Main Page (http:/ / www. japanvehicles. com/ newcars/ toyota/ Caldina/ main. htm)
[7] Toyota Alphard Hybrid Van (Available in Japan) (http:/ / localdc. com/ alphardhybrid. htm)
[8] LKA - Safetytoyota.com (http:/ / www. safetytoyota. com/ en-gb/ lane_keeping_assist. html#tab_technology)
[9] "Lexus LS 460 safety features" (http:/ / www. lexus-europe. com/ lexus_cars/ ls/ ls460/ showcase/ index. asp) (HTML). Lexus.co.uk. 2006. .
[10] LEXUS (http:/ / www. lexus. eu/ site-tools/ technology-glossary/ Index. aspx?index=JtoL)
[11] http:/ / www. youtube. com/ watch?v=gS_TxOIqLfg
[12] Honda Worldwide | World News | News Release | June 18, 2003 (http:/ / world. honda. com/ news/ 2003/ 4030618_2. html)
[13] The New Honda Legend (Acura RL) (http:/ / www. worldcarfans. com/ 2050301. 012/ the-new-honda-legend-acura-rl)
[14] Honda's lane-watching cruise control | Car Features | 4car | channel4.com (http:/ / www. channel4. com/ 4car/ ft/ feature/ feature/ 228/ 1)
[15] "Accord 2006 - Full Briefing" (http:/ / www. hondauk-media. co. uk/ uploads/ presspacks/ 5a02fe90161c72db29ce5d84babed2045eb84c6b/
Full_Briefing. pdf). Honda UK. 2006. .
[16] "Avoiding accidents" (http:/ / www. developpement-durable. psa. fr/ en/ realisation. php?niv1=5& niv2=52& niv3=2& id=2708). PSA
Peugeot Citroën. .
[17] The Audi Q7 4.2 TDI (http:/ / www. audiworld. com/ news/ 07/ audi-q7-42-tdi/ content. shtml)
[18] Audi allroad quattro concept (http:/ / audiworld. com/ news/ 05/ naias/ aaqc/ content5. shtml)
[19] Lane Keeping Assist: Steering wheel vibrates to warn the driver if the car leaves its lane unintentionally | Daimler Global Media Site >
Mercedes-Benz Cars > Mercedes-Benz P. ... (http:/ / media. daimler. com/ dcmedia/
0-921-614216-1-1147529-1-0-0-0-0-0-11702-0-0-1-0-0-0-0-0. html)
[20] (http:/ / www. springerlink. com/ content/ g432h69711k4286t/ )
[21] http:/ / www. IVsource. net


Non-photorealistic rendering
Non-photorealistic rendering (NPR) is an area of computer graphics that focuses on enabling a wide variety of
expressive styles for digital art. In contrast to traditional computer graphics, which has focused on photorealism,
NPR is inspired by artistic styles such as painting, drawing, technical illustration, and animated cartoons. NPR has
appeared in movies and video games in the form of "toon shaders," as well as in architectural illustration and
experimental animation. An example of a modern use of this method is that of Cel-shaded animation.

Three-Dimensional NPR Techniques
Three-dimensional NPR is the style that is most commonly seen in video games and movies. The output from this
technique is almost always a 3D model that has been modified from the original input model to portray a new artistic
style. In many cases, the geometry of the model is identical to the original geometry, and only the material applied to
the surface is modified. With increased availability of programmable GPU's, shaders have allowed NPR effects to be
applied to the rasterised image that is be displayed to the screen[1] . The majority of NPR techniques applied to 3D
geometry are intended to make the scene appear two-dimensional.

Two-Dimensional NPR Techniques
The input to a two-dimensional NPR system is most commonly an image; however, there are systems that take 3D
geometry information as input and produce a 2D image or video as output. Again, many of the systems are intended
to mimic a desired artistic style, such as watercolor, impressionism, or pen and ink drawing.

NPR for Enhancing Legibility
The most useful illustrations in technical illustrations are not necessarily photorealistic. Non-photorealistic
renderings, such as exploded view diagrams, greatly assist in showing placement of parts in a complex system.

Interactive Techniques
Users who are interested in having much more control in the NPR process may be more interested in interactive
techniques. Many of these NPR systems provide the user with a canvas that they can "paint" on using the cursor - as
the user paints, a stylized version of the image is revealed on the canvas. This is especially useful for people who
want to simulate different sizes of brush strokes according to different areas of the image.

Simulating the Artistic Media
In contrast to the methods mentioned previously, another technique in NPR is simulating the painter's medium.
Methods include simulating the diffusion of ink through different kinds of paper, and also of pigments through water
for simulation of watercolor.

Terminology
The term "non-photorealistic rendering" was probably coined by David Salesin and Georges Winkenbach in a 1994
paper. Many researchers find the terminology to be unsatisfying; some of the criticisms are as follows:
• The term "photorealism" means something different to graphics researchers than it does to artists, who are the
target consumers of NPR techniques. For artists, it refers to a school of painting that focuses on reproducing the
effect of a camera lens, with all the distortion and hyper-reflections that involves. For graphics researchers, it
refers to an image that is visually indistinguishable from reality. In fact, graphics researchers lump the kinds of
visual distortions that are used by photorealist painters into non-photorealism.


• Describing something by what it is not is problematic. Equivalent comparisons might be "non-elephant biology",
or "non-geometric mathematics". NPR researchers have stated that they expect the term will disappear eventually,
and be replaced by the more general term "computer graphics", with "photorealistic graphics" being used to
describe traditional computer graphics.
• Many techniques that are used to create 'non-photorealistic' images are not rendering techniques. They are
modelling techniques, or post-processing techniques. While the latter are coming to be known as 'image-based
rendering', sketch-based modelling techniques, cannot technically be included under this heading, which is very
inconvenient for conference organisers.
The first conference on Non-Photorealistic Animation and Rendering included a discussion of possible alternative
names. Among those suggested were "expressive graphics", "artistic rendering", "non-realistic graphics", "art-based
rendering", and "psychographics". All of these terms have been used in various research papers on the topic, but the
term NPR seems to have nonetheless taken hold.

References
Some key papers in the development of NPR are:
• "Paint by Numbers: Abstract Image Representations", by Paul Haeberli, SIGGRAPH 90
• "Comprehensible rendering of 3-D shapes", by Saito and Takahashi, SIGGRAPH 90
• "Wet and Sticky: A Novel Model for Computer-Based Painting", by Tunde Cockshott, PhD Thesis, Glasgow
University, 1991
• "Computer-Generated Pen-and-Ink Illustration", by Winkenbach and Salesin, SIGGRAPH 94
• "Interactive Pen-and-Ink Illustration", by Salisbury, Anderson, Barzel, Salesin, SIGGRAPH 94
• "Painterly Rendering for Animation", by Barb Meier, SIGGRAPH 96
• "A Non-Photorealistic Lighting Model For Automatic Technical Illustration", by Amy Gooch, Bruce Gooch,
Peter Shirley.Elaine Cohen, SIGGRAPH 98

Technical Meetings on NPR
The first technical meeting dedicated to NPR was the ACM sponsored Symposium on Non-Photorealistic Rendering
and Animation[2] (NPAR) in 2000. NPAR is traditionally co-located with the Annecy Animated Film Festival[3] ,
running on even numbered years. From 2007 NPAR began to also run on odd-numbered years, co-located with ACM
SIGGRAPH[4] .

Films and software that use NPR
This section lists some seminal uses of NPR techniques in films and software. See the article on cel-shaded
animation for a list of uses of toon-shading in games and movies.

Short films
• Technological Threat, 1988. Early use of toon shading together with Tex Avery-style cartoon characters.
• Gas Planet, by Eric Darnell, 1992. Pencil-sketching 3D rendering.
• Fishing by David Gainey, 2000. Watercolor-style 3D rendering.
• RoadHead, 1998 and Snack and Drink, 1999, by Bob Sabiston. Short films created with Rotoshop.
• Ryan, 2004. Nonlinear projection and other distortions of 3D geometry.


Feature films
• What Dreams May Come, 1998. Painterly rendering in the "painted world" sequence.
• Tarzan, 1999. First use of Disney's "Deep Canvas" system.
• Waking Life, 2001. First use of rotoshop in a feature film.
• Sin City, 2005.
• Renaissance, 2006.
• Azur et Asmar, 2006.
• A Scanner Darkly, 2007.
• 300, 2007.
• Bolt, 2008.
• Tangled, 2010.

Video games and other software
• Jet Set Radio, 2000 Early use of toon-shading in video games.
• SketchUp, 2000 Sketch-like modelling software with toon rendering.
• The Legend of Zelda: The Wind Waker, 2002 and Phantom Hourglass, 2007
• XIII (video game), 2003
• Ōkami, 2006
• Team Fortress 2, 2007
• Prince of Persia, 2008
• Valkyria Chronicles, 2008
• Borderlands, 2009

External links
• Paul Haeberli's Impressionist applet [5]
• Artistic smoothing applet [6]
• Tunde Cockshott's Wet and Sticky revisited [7]
• Stylized Depiction in Computer Graphics: An annotated survey of online NPR resources [8]
• NPAR conference [9]
• Homepage of freeware program FotoSketcher to turn photos into art [10]
[1] http:/ / developer. amd. com/ media/ gpu_assets/ ShaderX_NPR. pdf
[2] http:/ / www. npar. org
[3] http:/ / www. annecy. org
[4] http:/ / www. siggraph. org
[5] http:/ / laminadesign. com/ explore/ impression/ index. html
[6] http:/ / www. cs. rug. nl/ ~imaging/ artisticsmoothing/ java/ ArtisticApplet. html
[7] http:/ / java. cms. livjm. ac. uk/ homepage/ staff/ cmsdengl/ ws
[8] http:/ / www. red3d. com/ cwr/ npr/
[9] http:/ / www. npar. org/
[10] http:/ / www. fotosketcher. com/


Medical image processing
Medical imaging is the technique and process used to create images of the human body (or parts and function
thereof) for clinical purposes (medical procedures seeking to reveal, diagnose or examine disease) or medical science
(including the study of normal anatomy and physiology). Although imaging of removed organs and tissues can be
performed for medical reasons, such procedures are not usually referred to as medical imaging, but rather are a part
of pathology.
As a discipline and in its widest sense, it is part of biological imaging and incorporates radiology (in the wider
sense), nuclear medicine, investigative radiological sciences, endoscopy, (medical) thermography, medical
photography and microscopy (e.g. for human pathological investigations).
Measurement and recording techniques which are not primarily designed to produce images, such as
electroencephalography (EEG), magnetoencephalography (MEG), Electrocardiography (EKG) and others, but which
produce data susceptible to be represented as maps (i.e. containing positional information), can be seen as forms of
medical imaging.

Overview
In the clinical context, medical imaging is generally equated to radiology or "clinical imaging" and the medical
practitioner responsible for interpreting (and sometimes acquiring) the images is a radiologist. Diagnostic
radiography designates the technical aspects of medical imaging and in particular the acquisition of medical images.
The radiographer or radiologic technologist is usually responsible for acquiring medical images of diagnostic
quality, although some radiological interventions are performed by radiologists. While radiology is an evaluation of
anatomy, nuclear medicine provides functional assessment.
As a field of scientific investigation, medical imaging constitutes a sub-discipline of biomedical engineering,
medical physics or medicine depending on the context: Research and development in the area of instrumentation,
image acquisition (e.g. radiography), modelling and quantification are usually the preserve of biomedical
engineering, medical physics and computer science; Research into the application and interpretation of medical
images is usually the preserve of radiology and the medical sub-discipline relevant to medical condition or area of
medical science (neuroscience, cardiology, psychiatry, psychology, etc) under investigation. Many of the techniques
developed for medical imaging also have scientific and industrial applications.
Medical imaging is often perceived to designate the set of techniques that noninvasively produce images of the
internal aspect of the body. In this restricted sense, medical imaging can be seen as the solution of mathematical
inverse problems. This means that cause (the properties of living tissue) is inferred from effect (the observed signal).
In the case of ultrasonography the probe consists of ultrasonic pressure waves and echoes inside the tissue show the
internal structure. In the case of projection radiography, the probe is X-ray radiation which is absorbed at different
rates in different tissue types such as bone, muscle and fat.

Imaging technology

Radiography
Two forms of radiographic images are in use in medical imaging; projection radiography and fluoroscopy, with the
latter being useful for intraoperative and catheter guidance. These 2D techniques are still in wide use despite the
advance of 3D tomography due to the low cost, high resolution, and depending on application, lower radiation
dosages. This imaging modality utilizes a wide beam of x rays for image acquisition and is the first imaging
technique available in modern medicine.


• Fluoroscopy produces real-time images of internal structures of the body in a similar fashion to radiography, but
employs a constant input of x-rays, at a lower dose rate. Contrast media, such as barium, iodine, and air are used
to visualize internal organs as they work. Fluoroscopy is also used in image-guided procedures when constant
feedback during a procedure is required. An image receptor is required to convert the radiation into an image after
it has passed through the area of interest. Early on this was a fluorescing screen, which gave way to an Image
Amplifier (IA) which was a large vacuum tube that had the receiving end coated with cesium iodide, and a mirror
at the opposite end. Eventually the mirror was replaced with a TV camera.
• Projectional radiographs, more commonly known as x-rays, are often used to determine the type and extent of a
fracture as well as for detecting pathological changes in the lungs. With the use of radio-opaque contrast media,
such as barium, they can also be used to visualize the structure of the stomach and intestines - this can help
diagnose ulcers or certain types of colon cancer.

Magnetic resonance imaging (MRI)
A magnetic resonance imaging instrument (MRI scanner), or "nuclear
magnetic resonance (NMR) imaging" scanner as it was originally
known, uses powerful magnets to polarise and excite hydrogen nuclei
(single proton) in water molecules in human tissue, producing a
detectable signal which is spatially encoded, resulting in images of the
body. MRI uses three electromagnetic fields: a very strong (on the
order of units of teslas) static magnetic field to polarize the hydrogen
nuclei, called the static field; a weaker time-varying (on the order of
1 kHz) field(s) for spatial encoding, called the gradient field(s); and a
weak radio-frequency (RF) field for manipulation of the hydrogen
nuclei to produce measurable signals, collected through an RF antenna.

Like CT, MRI traditionally creates a two dimensional image of a thin
"slice" of the body and is therefore considered a tomographic imaging
technique. Modern MRI instruments are capable of producing images
in the form of 3D blocks, which may be considered a generalisation of
A brain MRI representation
the single-slice, tomographic, concept. Unlike CT, MRI does not
involve the use of ionizing radiation and is therefore not associated
with the same health hazards. For example, because MRI has only been in use since the early 1980s, there are no
known long-term effects of exposure to strong static fields (this is the subject of some debate; see 'Safety' in MRI)
and therefore there is no limit to the number of scans to which an individual can be subjected, in contrast with X-ray
and CT. However, there are well-identified health risks associated with tissue heating from exposure to the RF field
and the presence of implanted devices in the body, such as pace makers. These risks are strictly controlled as part of
the design of the instrument and the scanning protocols used.

Because CT and MRI are sensitive to different tissue properties, the appearance of the images obtained with the two
techniques differ markedly. In CT, X-rays must be blocked by some form of dense tissue to create an image, so the
image quality when looking at soft tissues will be poor. In MRI, while any nucleus with a net nuclear spin can be
used, the proton of the hydrogen atom remains the most widely used, especially in the clinical setting, because it is
so ubiquitous and returns a large signal. This nucleus, present in water molecules, allows the excellent soft-tissue
contrast achievable with MRI.


Nuclear medicine
Nuclear medicine encompasses both diagnostic imaging and treatment of disease, and may also be referred to as
molecular medicine or molecular imaging & therapeutics [1] . Nuclear medicine uses certain properties of isotopes
and the energetic particles emitted from radioactive material to diagnose or treat various pathology. Different from
the typical concept of anatomic radiology, nuclear medicine enables assessment of physiology. This function-based
approach to medical evaluation has useful applications in most subspecialties, notably oncology, neurology, and
cardiology. Gamma cameras are used in e.g. scintigraphy, SPECT and PET to detect regions of biologic activity that
may be associated with disease. Relatively short lived isotope, such as 123I is administered to the patient. Isotopes
are often preferentially absorbed by biologically active tissue in the body, and can be used to identify tumors or
fracture points in bone. Images are acquired after collimated photons are detected by a crystal that gives off a light
signal, which is in turn amplified and converted into count data.
• Scintigraphy ("scint") is a form of diagnostic test wherein radioisotopes are taken internally, for example
intravenously or orally. Then, gamma camera capture and form two-dimensional[2] images from the radiation
emitted by the radiopharmaceuticals.
• SPECT is a 3D tomographic technique that uses gamma camera data from many projections and can be
reconstructed in different planes. A dual detector head gamma camera combined with a CT scanner, which
provides localization of functional SPECT data, is termed a SPECT/CT camera, and has shown utility in
advancing the field of molecular imaging.
• Positron emission tomography (PET) uses coincidence detection to image functional processes. Short-lived
positron emitting isotope, such as 18F, is incorporated with an organic substance such as glucose, creating
F18-fluorodeoxyglucose, which can be used as a marker of metabolic utilization. Images of activity distribution
throughout the body can show rapidly growing tissue, like tumor, metastasis, or infection. PET images can be
viewed in comparison to computed tomography scans to determine an anatomic correlate. Modern scanners
combine PET with a CT, or even MRI, to optimize the image reconstruction involved with positron imaging. This
is performed on the same equipment without physically moving the patient off of the gantry. The resultant hybrid
of functional and anatomic imaging information is a useful tool in non-invasive diagnosis and patient
management.

Photoacoustic imaging
Photoacoustic imaging is a recently developed hybrid biomedical imaging modality based on the photoacoustic
effect. It combines the advantages of optical absorption contrast with ultrasonic spatial resolution for deep imaging
in (optical) diffusive or quasi-diffusive regime. Recent studies have shown that photoacoustic imaging can be used in
vivo for tumor angiogenesis monitoring, blood oxygenation mapping, functional brain imaging, and skin melanoma
detection, etc.

Breast Thermography
Digital infrared imaging thermography is based on the principle that metabolic activity and vascular circulation in
both pre-cancerous tissue and the area surrounding a developing breast cancer is almost always higher than in normal
breast tissue. Cancerous tumors require an ever-increasing supply of nutrients and therefore increase circulation to
their cells by holding open existing blood vessels, opening dormant vessels, and creating new ones
(neoangiogenesis). This process frequently results in an increase in regional surface temperatures of the breast.
Digital infrared imaging uses extremely sensitive medical infrared cameras and sophisticated computers to detect,
analyze, and produce high-resolution diagnostic images of these temperature variations. Because of DII's sensitivity,
these temperature variations may be among the earliest signs of breast cancer and/or a pre-cancerous state of the
breast[3] .


Tomography
Tomography is the method of imaging a single plane, or slice, of an object resulting in a tomogram. There are
several forms of tomography:
• Linear tomography: This is the most basic form of tomography. The X-ray tube moved from point "A" to point
"B" above the patient, while the cassette holder (or "bucky") moves simultaneously under the patient from point
"B" to point "A." The fulcrum, or pivot point, is set to the area of interest. In this manner, the points above and
below the focal plane are blurred out, just as the background is blurred when panning a camera during exposure.
No longer carried out and replaced by computed tomography.
• Poly tomography: This was a complex form of tomography. With this technique, a number of geometrical
movements were programmed, such as hypocycloidic, circular, figure 8, and elliptical. Philips Medical Systems
[4] produced one such device called the 'Polytome.' This unit was still in use into the 1990s, as its resulting
images for small or difficult physiology, such as the inner ear, was still difficult to image with CTs at that time.
As the resolution of CTs got better, this procedure was taken over by the CT.
• Zonography: This is a variant of linear tomography, where a limited arc of movement is used. It is still used in
some centres for visualising the kidney during an intravenous urogram (IVU).
• Orthopantomography (OPT or OPG): The only common tomographic examination in use. This makes use of a
complex movement to allow the radiographic examination of the mandible, as if it were a flat bone. It is often
referred to as a "Panorex", but this is incorrect, as it is a trademark of a specific company.
• Computed Tomography (CT), or Computed Axial Tomography (CAT: A CT scan, also known as a CAT scan, is
a helical tomography (latest generation), which traditionally produces a 2D image of the structures in a thin
section of the body. It uses X-rays. It has a greater ionizing radiation dose burden than projection radiography;
repeated scans must be limited to avoid health effects.

Ultrasound
Medical ultrasonography uses high frequency broadband sound waves in the megahertz range that are reflected by
tissue to varying degrees to produce (up to 3D) images. This is commonly associated with imaging the fetus in
pregnant women. Uses of ultrasound are much broader, however. Other important uses include imaging the
abdominal organs, heart, breast, muscles, tendons, arteries and veins. While it may provide less anatomical detail
than techniques such as CT or MRI, it has several advantages which make it ideal in numerous situations, in
particular that it studies the function of moving structures in real-time, emits no ionizing radiation, and contains
speckle that can be used in elastography. It is very safe to use and does not appear to cause any adverse effects,
although information on this is not well documented. It is also relatively inexpensive and quick to perform.
Ultrasound scanners can be taken to critically ill patients in intensive care units, avoiding the danger caused while
moving the patient to the radiology department. The real time moving image obtained can be used to guide drainage
and biopsy procedures. Doppler capabilities on modern scanners allow the blood flow in arteries and veins to be
assessed.


Medical imaging topics

Maximizing imaging procedure use
The amount of data obtained in a single MR or CT scan is very extensive. Some of the data that radiologists discard
could save patients time and money, while reducing their exposure to radiation and risk of complications from
invasive procedures.[5]

Creation of three-dimensional images
Recently, techniques have been developed to enable CT, MRI and ultrasound scanning software to produce 3D
images for the physician.[6] Traditionally CT and MRI scans produced 2D static output on film. To produce 3D
images, many scans are made, then combined by computers to produce a 3D model, which can then be manipulated
by the physician. 3D ultrasounds are produced using a somewhat similar technique. In diagnosing disease of the
viscera of abdomen,ultrasound is particularly sensitive on imaging of biliary tract,urinary tract and female
reproductive organs(ovary,fallopian tubes).As for example,diagnosis of gall stone by dilatation of common bile duct
and stone in common bile duct . With the ability to visualize important structures in great detail, 3D visualization
methods are a valuable resource for the diagnosis and surgical treatment of many pathologies. It was a key resource
for the famous, but ultimately unsuccessful attempt by Singaporean surgeons to separate Iranian twins Ladan and
Laleh Bijani in 2003. The 3D equipment was used previously for similar operations with great success.
Other proposed or developed techniques include:
• Diffuse optical tomography
• Elastography
• Electrical impedance tomography
• Optoacoustic imaging
• Ophthalmology
• A-scan
• B-scan
• Corneal topography
• Optical coherence tomography
• Scanning laser ophthalmoscopy
Some of these techniques are still at a research stage and not yet used in clinical routines.

Compression of medical images
Medical imaging techniques produce very large amounts of data, especially from CT, MRI and PET modalities. As a
result, storage and communications of electronic image data are prohibitive without the use of compression. JPEG
2000 is the state-of-the-art image compression DICOM standard for storage and transmission of medical images.
The cost and feasibility of accessing large image data sets over low or various bandwidths are further addressed by
use of another DICOM standard, called JPIP, to enable efficient streaming of the JPEG 2000 compressed image data.


Non-diagnostic imaging
Neuroimaging has also been used in experimental circumstances to allow people (especially disabled persons) to
control outside devices, acting as a brain computer interface.

Archiving and recording
Used primarily in ultrasound imaging, capturing the image a medical imaging device is required for archiving and
telemedicine applications. In most scenarios, a frame grabber is used in order to capture the video signal from the
medical device and relay it to a computer for further processing and operations.[7]

Open source software for medical image analysis
Several open source software packages are available for performing analysis of medical images:
• ImageJ
• 3D Slicer
• ITK
• OsiriX
• GemIdent
• MicroDicom
• FreeSurfer
• FreePlugin

Use in pharmaceutical clinical trials
Medical imaging has become a major tool in clinical trials since it enables rapid diagnosis with visualization and
quantitative assessment.
A typical clinical trial goes through multiple phases and can take up to eight years. Clinical endpoints or outcomes
are used to determine whether the therapy is safe and effective. Once a patient reaches the endpoint, he/she is
generally excluded from further experimental interaction. Trials that rely solely on clinical endpoints are very costly
as they have long durations and tend to need large number of patients.
In contrast to clinical endpoints, surrogate endpoints have been shown to cut down the time required to confirm
whether a drug has clinical benefits. Imaging biomarkers (a characteristic that is objectively measured by an imaging
technique, which is used as an indicator of pharmacological response to a therapy) and surrogate endpoints have
shown to facilitate the use of small group sizes, obtaining quick results with good statistical power.[8]
Imaging is able to reveal subtle change that is indicative of the progression of therapy that may be missed out by
more subjective, traditional approaches. Statistical bias is reduced as the findings are evaluated without any direct
patient contact.
For example, measurement of tumour shrinkage is a commonly used surrogate endpoint in solid tumour response
evaluation. This allows for faster and more objective assessment of the effects of anticancer drugs. In evaluating the
extent of Alzheimer’s disease, it is still prevalent to use behavioural and cognitive tests. MRI scans on the entire
brain can accurately pinpoint hippocampal atrophy rate while PET scans is able to measure the brain’s metabolic
activity by measuring regional glucose metabolism.[8]
An imaging-based trial will usually be made up of three components:
1. A realistic imaging protocol. The protocol is an outline that standardizes (as far as practically possible) the way in
which the images are acquired using the various modalities (PET, SPECT, CT, MRI). It covers the specifics in
which images are to be stored, processed and evaluated.
2. An imaging centre that is responsible for collecting the images, perform quality control and provide tools for data
storage, distribution and analysis. It is important for images acquired at different time points are displayed in a


standardised format to maintain the reliability of the evaluation. Certain specialised imaging contract research
organizations provide to end medical imaging services, from protocol design and site management through to data
quality assurance and image analysis.
3. Clinical sites that recruit patients to generate the images to send back to the imaging centre.

See also
• Preclinical imaging • Magnetic field imaging • Pneumoencephalogram
• Cardiac PET • Medical examination • Radiology information system
• Biomedical informatics • Medical radiography • Segmentation (image processing)
• Digital Imaging and Communications in • Medical test • Signal-to-noise ratio
Medicine
• Digital Mammography and PACS • Neuroimaging • Society for Imaging Science and Technology
• EMMI European Master in Molecular Imaging • Non-invasive (medical) • Tomogram
• Fotofinder • PACS • Virtopsy
• Full-body scan • JPEG 2000
compression
• VoluMedic • JPIP streaming

Further reading
• Burger, Wilhelm; Burge, Mark James, eds (2008). Digital Image Processing: An Algorithmic Introduction using
Java. Texts in Computer Science series. New York: Springer Science+Business Media.
doi:10.1007/978-1-84628-968-2. ISBN 978-1-84628-379-6.
• Baert, Albert L., ed (2008). Encyclopedia of Diagnostic Imaging. Berlin: Springer-Verlag.
doi:10.1007/978-3-540-35280-8. ISBN 978-3-540-35278-5.
• Tony F. Chan and Jackie Shen (2005). Image Processing and Analysis - Variational, PDE, Wavelet, and
Stochastic Methods [9]. SIAM
• Terry Yoo(Editor) (2004), Insight into Images.
• Robb, RA (1999). Biomedical Imaging, Visualization, and Analysis. John Wiley & Sons, Inc. ISBN 0471283533.
• Journal of Digital Imaging (New York: Springer Science+Business Media). ISSN 0897-1889.
• Using JPIP for Standard-Compliant Sharing of Medical Image Data [10] a white paper by Aware Inc. [11]

External links
• Medical imaging [12] at the Open Directory Project
• Medical Image Database [13] Free Indexed Online Images
• http://www.aware.com/imaging/accuradjpip.htm What is JPIP?

References
[1] Society of Nuclear Medicine (http:/ / www. snm. org)
[2] thefreedictionary.com > scintigraphy (http:/ / medical-dictionary. thefreedictionary. com/ scintigraphy) Citing: Dorland's Medical Dictionary
for Health Consumers, 2007 by Saunders; Saunders Comprehensive Veterinary Dictionary, 3 ed. 2007; McGraw-Hill Concise Dictionary of
Modern Medicine, 2002 by The McGraw-Hill Companies
[3] http:/ / www. breastthermography. com/ breast_thermography_mf. htm
[4] http:/ / www. medical. philips. com/ main/ index. asp
[5] Freiherr G. Waste not, want not: Getting the most from imaging procedures (http:/ / www. diagnosticimaging. com/ news/ display/ article/
113619/ 1541872). Diagnostic Imaging. March 19, 2010.
[6] Udupa, J.K. and Herman, G. T., 3D Imaging in Medicine, 2nd Edition, CRC Press, 2000
[7] Treating Medical Ailments in Real Time (http:/ / www. epiphan. com/ solutions_new/ ?arid=16)


[8] Hajnal, J. V., Hawkes, D. J., & Hill, D. L. (2001). Medical Image Registration. CRC Press.
[9] http:/ / jackieneoshen. googlepages. com/ ImagingNewEra. html
[10] http:/ / www. aware. com/ imaging/ whitepapers/ wp_jpipwado. htm
[11] http:/ / www. aware. com/ imaging/ whitepapers. htm
[12] http:/ / www. dmoz. org/ Health/ Medicine/ Imaging/ /
[13] http:/ / rad. usuhs. edu/ medpix/ index. html?

Microscope image processing
Microscope image processing is a broad term that covers the use of digital image processing techniques to process,
analyze and present images obtained from a microscope. Such processing is now commonplace in a number of
diverse fields such as medicine, biological research, cancer research, drug testing, metallurgy, etc. A number of
manufacturers of microscopes now specifically design in features that allow the microscopes to interface to an image
processing system.

Image acquisition
Until the early 1990s, most image acquisition in video microscopy applications was typically done with an analog
video camera, often simply closed circuit TV cameras. While this required the use of a frame grabber to digitize the
images, video cameras provided images at full video frame rate (25-30 frames per second) allowing live video
recording and processing. While the advent of solid state detectors yielded several advantages, the real-time video
camera was actually superior in many respects.
Today, acquisition is usually done using a CCD camera mounted in the optical path of the microscope. The camera
may be full colour or monochrome. Very often, very high resolution cameras are employed to gain as much direct
information as possible. Cryogenic cooling is also common, to minimise noise. Often digital cameras used for this
application provide pixel intensity data to a resolution of 12-16 bits, much higher than is used in consumer imaging
products.
Ironically, in recent years, much effort has been put into acquiring data at video rates, or higher (25-30 frames per
second or higher). What was once easy with off-the-shelf video cameras now requires special, high speed electronics
to handle the vast digital data bandwidth.
Higher speed acquisition allows dynamic processes to be observed in real time, or stored for later playback and
analysis. Combined with the high image resolution, this approach can generate vast quantities of raw data, which can
be a challenge to deal with, even with a modern computer system.
It should be observed that while current CCD detectors allow very high image resolution, often this involves a
trade-off because, for a given chip size, as the pixel count increases, the pixel size decreases. As the pixels get
smaller, their well depth decreases, reducing the number of electrons that can be stored. In turn, this results in a
poorer signal to noise ratio.
For best results, one must select an appropriate sensor for a given application. Because microscope images have an
intrinsic limiting resolution, it often makes little sense to use a noisy, high resolution detector for image acquisition.
A more modest detector, with larger pixels, can often produce much higher quality images because of reduced noise.
This is especially important in low-light applications such as fluorescence microscopy.
Moreover, one must also consider the temporal resolution requirements of the application. A lower resolution
detector will often have a significantly higher acquisition rate, permitting the observation of faster events.
Conversely, if the observed object is motionless, one may wish to acquire images at the highest possible spatial
resolution without regard to the time required to acquire a single image.


2D image techniques
Image processing for microscopy application begins with fundamental techniques intended to most accurately
reproduce the information contained in the microscopic sample. This might include adjusting the brightness and
contrast of the image, averaging images to reduce image noise and correcting for illumination non-uniformities. Such
processing involves only basic arithmetic operations between images (i.e. addition, subtraction, multiplication and
division). The vast majority of processing done on microscope image is of this nature.
Another class of common 2D operations called image convolution are often used to reduce or enhance image details.
Such "blurring" and "sharpening" algorithms in most programs work by altering a pixel's value based on a weighted
sum of that and the surrounding pixels. (a more detailed description of kernel based convolution deserves an entry
for itself).
Other basic two dimensional techniques include operations such as image rotation, warping, color balancing etc.
At times, advanced techniques are employed with the goal of "undoing" the distortion of the optical path of the
microscope, thus eliminating distortions and blurring caused by the instrumentation. This process is called
deconvolution, and a variety of algorithms have been developed, some of great mathematical complexity. The end
result is an image far sharper and clearer than could be obtained in the optical domain alone. This is typically a
3-dimensional operation, that analyzes a volumetric image (i.e. images taken at a variety of focal planes through the
sample) and uses this data to reconstruct a more accurate 3-dimensional image.

3D image techniques
Another common requirement is to take a series of images at a fixed position, but at different focal depths. Since
most microscopic samples are essentially transparent, and the depth of field of the focused sample is exceptionally
narrow, it is possible to capture images "through" a three-dimensional object using 2D equipment like confocal
microscopes. Software is then able to reconstruct a 3D model of the original sample which may be manipulated
appropriately. The processing turns a 2D instrument into a 3D instrument, which would not otherwise exist. In recent
times this technique has led to a number of scientific discoveries in cell biology.

Analysis
Analysis of images will vary considerably according to application. Typical analysis includes determining where the
edges of an object are, counting similar objects, calculating the area, perimeter length and other useful measurements
of each object. A common approach is to create an image mask which only includes pixels that match certain
criteria, then perform simpler scanning operations on the resulting mask. It is also possible to label objects and track
their motion over a series of frames in a video sequence.

References
Russ, John C. (2006-12-19) [1992]. The Image Processing Handbook (5th edition ed.). CRC Press.
ISBN 0849372542.
• Jan-Mark Geusebroek, Color and Geometrical Structure in Images, Applications in Microscopy, ISBN
90-5776-057-6
• Young Ian T., Not just pretty pictures: Digital quantitative microscopy, Proc. Royal Microscopical Society, 1996,
31(4), pp. 311-313.
• Young Ian T., Quantitative Microscopy, IEEE Engineering in Medicine and Biology, 1996, 15(1), pp. 59-66.
• Young Ian T., Sampling density and quantitative microscopy, Analytical and Quantitative Cytology and
Histology, vol. 10, 1988, pp. 269-275


See also
• Image processing
• ImageJ
• FIJI (software)
• Endrov
• GemIdent

External links
• Quantitative Microscopy [1]
• 3-D Image Processing in Microscopy [2]
• Sampling theorem [3] - Nyquist sampling in digital microscopy

References
[1] http:/ / www. ph. tn. tudelft. nl/ People/ young/ manuscripts/ QM/ QM. html
[2] http:/ / www. med. uni-giessen. de/ ipl/ iplcourse. html
[3] http:/ / www. vanosta. be/ pcrnyq. htm

Morphological image processing
Mathematical morphology (MM) is a theory and technique for the
analysis and processing of geometrical structures, based on set theory,
lattice theory, topology, and random functions. MM is most commonly
applied to digital images, but it can be employed as well on graphs,
surface meshes, solids, and many other spatial structures.
Topological and geometrical continuous-space concepts such as size,
shape, convexity, connectivity, and geodesic distance, can be
characterized by MM on both continuous and discrete spaces. MM is
also the foundation of morphological image processing, which consists
of a set of operators that transform images according to the above
characterizations.

MM was originally developed for binary images, and was later
extended to grayscale functions and images. The subsequent
generalization to complete lattices is widely accepted today as MM's A shape (in blue) and its morphological dilation
theoretical foundation. (in green) and erosion (in yellow) by a
diamond-shape structuring element.

History
Mathematical Morphology was born in 1964 from the collaborative work of Georges Matheron and Jean Serra, at the
École des Mines de Paris, France. Matheron supervised the PhD thesis of Serra, devoted to the quantification of
mineral characteristics from thin cross sections, and this work resulted in a novel practical approach, as well as
theoretical advancements in integral geometry and topology.
In 1968, the Centre de Morphologie Mathématique was founded by the École des Mines de Paris in Fontainebleau,
France, lead by Matheron and Serra.


During the rest of the 1960's and most of the 1970's, MM dealt essentially with binary images, treated as sets, and
generated a large number of binary operators and techniques: Hit-or-miss transform, dilation, erosion, opening,
closing, granulometry, thinning, skeletonization, ultimate erosion, conditional bisector, and others. A random
approach was also developed, based on novel image models. Most of the work in that period was developed in
Fontainebleau.
From mid-1970's to mid-1980's, MM was generalized to grayscale functions and images as well. Besides extending
the main concepts (such as dilation, erosion, etc...) to functions, this generalization yielded new operators, such as
morphological gradients, top-hat transform and the Watershed (MM's main segmentation approach).
In the 1980's and 1990's, MM gained a wider recognition, as research centers in several countries began to adopt and
investigate the method. MM started to be applied to a large number of imaging problems and applications.
In 1986, Jean Serra further generalized MM, this time to a theoretical framework based on complete lattices. This
generalization brought flexibility to the theory, enabling its application to a much larger number of structures,
including color images, video, graphs, meshes, etc... At the same time, Matheron and Serra also formulated a theory
for morphological filtering, based on the new lattice framework.
The 1990's and 2000's also saw further theoretical advancements, including the concepts of connections and
levelings.
In 1993, the first International Symposium on Mathematical Morphology (ISMM) took place in Barcelona, Spain.
Since then, ISMMs are organized every 2-3 years, each time in a different part of the world: Fontainebleau, France
(1994); Atlanta, USA (1996); Amsterdam, Netherlands (1998); Palo Alto, CA, USA (2000); Sydney, Australia
(2002); Paris, France (2004); Rio de Janeiro, Brazil (2007); and Groningen, Netherlands (2009).

References
• "Introduction" by Pierre Soille, in (Serra et al. (Eds.) 1994), pgs. 1-4.
• "Appendix A: The 'Centre de Morphologie Mathématique', an overview" by Jean Serra, in (Serra et al. (Eds.)
1994), pgs. 369-374.
• "Foreword" in (Ronse et al. (Eds.) 2005)

Binary morphology
In binary morphology, an image is viewed as a subset of an Euclidean space or the integer grid , for some
dimension d.

Structuring element
The basic idea in binary morphology is to probe an image with a simple, pre-defined shape, drawing conclusions on
how this shape fits or misses the shapes in the image. This simple "probe" is called structuring element, and is itself a
binary image (i.e., a subset of the space or grid).
Here are some examples of widely used structuring elements (denoted by B):
• Let ; B is an open disk of radius r, centered at the origin.
• Let ; B is a 3x3 square, that is, B={(-1,-1), (-1,0), (-1,1), (0,-1), (0,0), (0,1), (1,-1), (1,0), (1,1)}.
• Let ; B is the "cross" given by: B={(-1,0), (0,-1), (0,0), (0,1), (1,0)}.


Basic operators
The basic operations are shift-invariant (translation invariant) operators strongly related to Minkowski addition.
Let E be a Euclidean space or an integer grid, and A a binary image in E.

Erosion

The erosion of the binary image A by the structuring element B is
defined by:

The erosion of the dark-blue square by a disk,
resulting in the light-blue square.

,
where Bz is the translation of B by the vector z, i.e., , .
When the structuring element B has a center (e.g., B is a disk or a square), and this center is located on the origin of
E, then the erosion of A by B can be understood as the locus of points reached by the center of B when B moves
inside A. For example, the erosion of a square of side 10, centered at the origin, by a disc of radius 2, also centered at
the origin, is a square of side 6 centered at the origin.

The erosion of A by B is also given by the expression: .

Example application: Assume we have received a fax of a dark photocopy. Everything looks like it was written with
a pen that is bleeding. Erosion process will allow thicker lines to get skinny and detect the hole inside the letter "o".


Dilation

The dilation of A by the structuring element B is defined by:

The dilation of the dark-blue square by a disk,
resulting in the light-blue square with rounded
corners.

.

The dilation is commutative, also given by: .

If B has a center on the origin, as before, then the dilation of A by B can be understood as the locus of the points
covered by B when the center of B moves inside A. In the above example, the dilation of the square of side 10 by the
disk of radius 2 is a square of side 14, with rounded corners, centered at the origin. The radius of the rounded corners
is 2.
The dilation can also be obtained by: , where Bs denotes the symmetric of
B, that is, .
Example application: Dilation is the opposite of the erosion. Figures that are very lightly drawn get thick when
"dilated". Easiest way to describe it is to imagine the same fax/text is written with a thicker pen.

Opening

The opening of A by B is obtained by the erosion of A by B, followed
by dilation of the resulting image by B:

The opening of the dark-blue square by a disk,
resulting in the light-blue square with round
corners.

.


The opening is also given by , which means that it is the locus of translations of the structuring

element B inside the image A. In the case of the square of radius 10, and a disc of radius 2 as the structuring element,
the opening is a square of radius 10 with rounded corners, where the corner radius is 2.
Example application: Let's assume someone has written a note on a non-soaking paper that writing looks like it is
growing tiny hairy roots all over. Opening essentially removes the outer tiny "hairline" leaks and restores the text.
The side effect is that it rounds off things. The sharp edges start to disappear.

Closing

The closing of A by B is obtained by the dilation of A by B, followed
by erosion of the resulting structure by B:

The closing of the dark-blue shape (union of two
squares) by a disk, resulting in the union of the
dark-blue shape and the light-blue areas.

.
The closing can also be obtained by , where Xc denotes the complement of X relative to E
(that is, ). The above means that the closing is the complement of the locus of
translations of the symmetric of the structuring element outside the image A.

Properties of the basic operators
Here are some properties of the basic binary morphological operators (dilation, erosion, opening and closing):
• They are translation invariant.
• They are increasing, that is, if , then , and , etc.
• The dilation is commutative.
• If the origin of E belongs to the structuring element B, then .
• The dilation is associative, i.e., . Moreover, the erosion satisfies
.
• Erosion and dilation satisfy the duality .
• Opening and closing satisfy the duality .
• The dilation is distributive over set union
• The erosion is distributive over set intersection
• The dilation is a pseudo-inverse of the erosion, and vice-versa, in the following sense: if and
only if .
• Opening and closing are idempotent.
• Opening is anti-extensive, i.e., , whereas the closing is extensive, i.e., .


Other operators and tools
• Hit-or-miss transform
• Morphological skeleton
• Filtering by reconstruction
• Ultimate erosions and conditional bisectors
• Granulometry
• Geodesic distance functions

Grayscale morphology
In grayscale morphology, images are functions mapping an Euclidean space or grid E into ,
where is the set of reals, is an element larger than any real number, and is an element smaller than any
real number.
Grayscale structuring elements are also functions of the same format, called "structuring functions".
Denoting an image by f(x) and the structuring function by b(x), the grayscale dilation of f by b is given by

,
where "sup" denotes the supremum.
Similarly, the erosion of f by b is given by

,
where "inf" denotes the infimum.
Just like in binary morphology, the opening and closing are given respectively by
, and
.

Flat structuring functions
It is common to use flat structuring elements in morphological applications. Flat structuring functions are functions
b(x) in the form

,

where .
In this case, the dilation and erosion are greatly simplified, and given respectively by

, and

.
In the bounded, discrete case (E is a grid and B is bounded), the supremum and infimum operators can be replaced
by the maximum and minimum. Thus, dilation and erosion are particular cases of order statistics filters, with dilation
returning the maximum value within a moving window (the symmetric of the structuring function support B), and
the erosion returning the minimum value within the moving window B.
In the case of flat structuring element, the morphological operators depend only on the relative ordering of pixel
values, regardless their numerical values, and therefore are especially suited to the processing of binary images and
grayscale images whose light transfer function is not known.


Other operators and tools
• Morphological Gradients
• Top-hat transform
• Watershed (algorithm)
By combining these operators one can obtain algorithms for many image processing tasks, such as feature detection,
image segmentation, image sharpening, image filtering, and classification.

Mathematical morphology on complete lattices
Complete lattices are partially ordered sets, where every subset has an infimum and a supremum. In particular, it
contains a least element and a greatest element (also denoted "universe").

Adjunctions (Dilation and Erosion)
Let be a complete lattice, with infimum and minimum symbolized by and , respectively. Its universe
and least element are symbolized by U and , respectively. Moreover, let be a collection of elements from
L.
A dilation is any operator that distributes over the supremum, and preserves the least element. I.e.:

• ,

• .
An erosion is any operator that distributes over the infimum, and preserves the universe. I.e.:

• ,

• .
Dilations and erosions form Galois connections. That is, for all dilation there is one and only one erosion that
satisfies

for all .
Similarly, for all erosion there is one and only one dilation satisfying the above connection.
Furthermore, if two operators satisfy the connection, then must be a dilation, and an erosion.
Pairs of erosions and dilations satisfying the above connection are called "adjunctions", and the erosion is said to be
the adjoint erosion of the dilation, and vice-versa.

Opening and Closing
For all adjunction , the morphological opening and morphological closing are
defined as follows:
, and
.
The morphological opening and closing are particular cases of algebraic opening (or simply opening) and algebraic
closing (or simply closing). Algebraic openings are operators in L that are idempotent, increasing, and anti-extensive.
Algebraic closings are operators in L that are idempotent, increasing, and extensive.


Particular cases
Binary morphology is a particular case of lattice morphology, where L is the power set of E (Euclidean space or
grid), that is, L is the set of all subsets of E, and is the set inclusion. In this case, the infimum is set intersection,
and the supremum is set union.
Similarly, grayscale morphology is another particular case, where L is the set of functions mapping E into
, and , , and , are the point-wise order, supremum, and infimum, respectively. That is,
is f and g are functions in L, then if and only if ; the infimum is given by
; and the supremum is given by .

References
• Image Analysis and Mathematical Morphology by Jean Serra, ISBN 0126372403 (1982)
• Image Analysis and Mathematical Morphology, Volume 2: Theoretical Advances by Jean Serra, ISBN
0-12-637241-1 (1988)
• An Introduction to Morphological Image Processing by Edward R. Dougherty, ISBN 0-8194-0845-X (1992)
• Morphological Image Analysis; Principles and Applications by Pierre Soille, ISBN 3540-65671-5 (1999), 2nd
edition (2003)
• Mathematical Morphology and its Application to Signal Processing, J. Serra and Ph. Salembier (Eds.),
proceedings of the 1st international symposium on mathematical morphology (ISMM'93), ISBN 84-7653-271-7
(1993)
• Mathematical Morphology and Its Applications to Image Processing, J. Serra and P. Soille (Eds.), proceedings of
the 2nd international symposium on mathematical morphology (ISMM'93), ISBN 0-7923-3093-5 (1994)
• Mathematical Morphology and its Applications to Image and Signal Processing, Henk J.A.M. Heijmans and Jos
B.T.M. Roerdink (Eds.), proceedings of the 4th international symposium on mathematical morphology
(ISMM'98), ISBN 0-7923-5133-9 (1998)
• Mathematical Morphology: 40 Years On, Christian Ronse, Laurent Najman, and Etienne Decencière (Eds.), ISBN
1-4020-3442-3 (2005)
• Mathematical Morphology and its Applications to Signal and Image Processing, Gerald J.F. Banon, Junior
Barrera, Ulisses M. Braga-Neto (Eds.), proceedings of the 8th international symposium on mathematical
morphology (ISMM'07), ISBN 978-85-17-00032-4 (2007)

External links
• Online course on mathematical morphology [1], by Jean Serra (in English, French, and Spanish)
• Center of Mathematical Morphology [2], Paris School of Mines
• History of Mathematical Morphology [3], by Georges Matheron and Jean Serra
• Morphology Digest, a newsletter on mathematical morphology [4], by Pierre Soille
• Lectures on Image Processing: A collection of 18 lectures in pdf format from Vanderbilt University. Lectures
16-18 are on Mathematical Morphology [3], by Alan Peters
• Mathematical Morphology; from Computer Vision lectures [5], by Robyn Owens
• Free SIMD Optimized Image processing library [6]
• Java applet demonstration [7]
• FILTERS : a free open source image processing library [8]
• Fast morphological erosions, dilations, openings, and closings [9]


References
[1] http:/ / cmm. ensmp. fr/ ~serra/ cours/ index. htm
[2] http:/ / cmm. ensmp. fr/ index_eng. html
[3] http:/ / cmm. ensmp. fr/ ~serra/ pdf/ birth_of_mm. pdf
[4] http:/ / mdigest. jrc. ec. europa. eu
[5] http:/ / homepages. inf. ed. ac. uk/ rbf/ CVonline/ LOCAL_COPIES/ OWENS/ LECT3/ node3. html
[6] http:/ / fulguro. sourceforge. net
[7] http:/ / www. cs. bris. ac. uk/ ~majid/ mengine/ morph. html
[8] http:/ / filters. sourceforge. net/
[9] http:/ / www. ulg. ac. be/ telecom/ research/ libmorphoDoc/ index. html

Remote sensing
Remote sensing is the small or large-scale acquisition of information of an
object or phenomenon, by the use of either recording or real-time sensing
device(s) that are wireless, or not in physical or intimate contact with the object
(such as by way of aircraft, spacecraft, satellite, buoy, or ship). In practice,
remote sensing is the stand-off collection through the use of a variety of devices
for gathering information on a given object or area. Thus, Earth observation or
weather satellite collection platforms, ocean and atmospheric observing weather
buoy platforms, the monitoring of a parolee via an ultrasound identification
system, Magnetic Resonance Imaging (MRI), Positron Emission Tomography
(PET), X-radiation (X-RAY) and space probes are all examples of remote
sensing. In modern usage, the term generally refers to the use of imaging sensor
technologies including: instruments found in aircraft and spacecraft as well as
those used in electrophysiology, and is distinct from other imaging-related fields
such as medical imaging.

There are two main types of remote sensing: passive remote sensing and active
remote sensing. Passive sensors detect natural radiation that is emitted or
reflected by the object or surrounding area being observed. Reflected sunlight is
the most common source of radiation measured by passive sensors. Examples of Synthetic aperture radar image of
Death Valley colored using
passive remote sensors include film photography, Infrared, charge-coupled
polarimetry.
devices, and radiometers. Active collection, on the other hand, emits energy in
order to scan objects and areas whereupon a sensor then detects and measures the
radiation that is reflected or backscattered from the target. RADAR is an example of active remote sensing where the
time delay between emission and return is measured, establishing the location, height, speed and direction of an
object.

Remote sensing makes it possible to collect data on dangerous or inaccessible areas. Remote sensing applications
include monitoring deforestation in areas such as the Amazon Basin, the effects of climate change on glaciers and
Arctic and Antarctic regions, and depth sounding of coastal and ocean depths. Military collection during the cold war
made use of stand-off collection of data about dangerous border areas. Remote sensing also replaces costly and slow
data collection on the ground, ensuring in the process that areas or objects are not disturbed.
Orbital platforms collect and transmit data from different parts of the electromagnetic spectrum, which in
conjunction with larger scale aerial or ground-based sensing and analysis, provides researchers with enough
information to monitor trends such as El Niño and other natural long and short term phenomena. Other uses include
different areas of the earth sciences such as natural resource management, agricultural fields such as land usage and

Remote sensing 68

conservation, and national security and overhead, ground-based and stand-off collection on border areas.[1]

Data acquisition techniques
The basis for multi-spectral collection and analysis is that of examined areas or objects that reflect or emit radiation
that stand out from surrounding areas.

Applications of remote sensing data
• Conventional radar is mostly associated with aerial traffic control, early warning, and certain large scale
meteorological data. Doppler radar is used by local law enforcements' monitoring of speed limits and in enhanced
meteorological collection such as wind speed and direction within weather systems. Other types of active
collection includes plasmas in the ionosphere). Interferometric synthetic aperture radar is used to produce precise
digital elevation models of large scale terrain (See RADARSAT, TerraSAR-X, Magellan).
• Laser and radar altimeters on satellites have provided a wide range of data. By measuring the bulges of water
caused by gravity, they map features on the seafloor to a resolution of a mile or so. By measuring the height and
wave-length of ocean waves, the altimeters measure wind speeds and direction, and surface ocean currents and
directions.
• Light detection and ranging (LIDAR) is well known in the examples of weapon ranging, laser illuminated homing
of projectiles.LIDAR discovered by hendy in 1976. LIDAR is used to detect and measure the concentration of
various chemicals in the atmosphere, while airborne LIDAR can be used to measure heights of objects and
features on the ground more accurately than with radar technology. Vegetation remote sensing is a principle
application of LIDAR.
• Radiometers and photometers are the most common instrument in use, collecting reflected and emitted radiation
in a wide range of frequencies. The most common are visible and infrared sensors, followed by microwave,
gamma ray and rarely, ultraviolet. They may also be used to detect the emission spectra of various chemicals,
providing data on chemical concentrations in the atmosphere.
• Stereographic pairs of aerial photographs have often been used to make topographic maps by imagery and terrain
analysts in trafficability and highway departments for potential routes.
• Simultaneous multi-spectral platforms such as Landsat have been in use since the 70's. These thematic mappers
take images in multiple wavelengths of electro-magnetic radiation (multi-spectral) and are usually found on earth
observation satellites, including (for example) the Landsat program or the IKONOS satellite. Maps of land cover
and land use from thematic mapping can be used to prospect for minerals, detect or monitor land usage,
deforestation, and examine the health of indigenous plants and crops, including entire farming regions or forests.
• Within the scope of the combat against desertification, remote sensing allows to follow-up and monitor risk areas
in the long term, to determine desertification factors, to support decision-makers in defining relevant measures of
environmental management, and to assess their impacts.[2]

Remote sensing 69

Geodetic
• Overhead geodetic collection was first used in aerial submarine detection and gravitational data used in military
maps. This data revealed minute perturbations in the Earth's gravitational field (geodesy) that may be used to
determine changes in the mass distribution of the Earth, which in turn may be used for geological or hydrological
studies.

Acoustic and near-acoustic
• Sonar: passive sonar, listening for the sound made by another object (a vessel, a whale etc); active sonar, emitting
pulses of sounds and listening for echoes, used for detecting, ranging and measurements of underwater objects
and terrain.
• Seismograms taken at different locations can locate and measure earthquakes (after they occur) by comparing the
relative intensity and precise timing.
To coordinate a series of large-scale observations, most sensing systems depend on the following: platform location,
what time it is, and the rotation and orientation of the sensor. High-end instruments now often use positional
information from satellite navigation systems. The rotation and orientation is often provided within a degree or two
with electronic compasses. Compasses can measure not just azimuth (i.e. degrees to magnetic north), but also
altitude (degrees above the horizon), since the magnetic field curves into the Earth at different angles at different
latitudes. More exact orientations require gyroscopic-aided orientation, periodically realigned by different methods
including navigation from stars or known benchmarks.
Resolution impacts collection and is best explained with the following relationship: less resolution=less detail &
larger coverage, More resolution=more detail, less coverage. The skilled management of collection results in
cost-effective collection and avoid situations such as the use of multiple high resolution data which tends to clog
transmission and storage infrastructure.

Data processing
Generally speaking, remote sensing works on the principle of the inverse problem. While the object or phenomenon
of interest (the state) may not be directly measured, there exists some other variable that can be detected and
measured (the observation), which may be related to the object of interest through the use of a data-derived
computer model. The common analogy given to describe this is trying to determine the type of animal from its
footprints. For example, while it is impossible to directly measure temperatures in the upper atmosphere, it is
possible to measure the spectral emissions from a known chemical species (such as carbon dioxide) in that region.
The frequency of the emission may then be related to the temperature in that region via various thermodynamic
relations.
The quality of remote sensing data consists of its spatial, spectral, radiometric and temporal resolutions.
Spatial resolution
The size of a pixel that is recorded in a raster image - typically pixels may correspond to square areas ranging
in side length from 1 to 1000 metres (3.3 to 3300 ft).
Spectral resolution
The wavelength width of the different frequency bands recorded - usually, this is related to the number of
frequency bands recorded by the platform. Current Landsat collection is that of seven bands, including several
in the infra-red spectrum, ranging from a spectral resolution of 0.07 to 2.1 μm. The Hyperion sensor on Earth
Observing-1 resolves 220 bands from 0.4 to 2.5 μm, with a spectral resolution of 0.10 to 0.11 μm per band.
Radiometric resolution

Remote sensing 70

The number of different intensities of radiation the sensor is able to distinguish. Typically, this ranges from 8
to 14 bits, corresponding to 256 levels of the gray scale and up to 16,384 intensities or "shades" of colour, in
each band. It also depends on the instrument noise.
Temporal resolution
The frequency of flyovers by the satellite or plane, and is only relevant in time-series studies or those requiring
an averaged or mosaic image as in deforesting monitoring. This was first used by the intelligence community
where repeated coverage revealed changes in infrastructure, the deployment of units or the
modification/introduction of equipment. Cloud cover over a given area or object makes it necessary to repeat
the collection of said location.
In order to create sensor-based maps, most remote sensing systems expect to extrapolate sensor data in relation to a
reference point including distances between known points on the ground. This depends on the type of sensor used.
For example, in conventional photographs, distances are accurate in the center of the image, with the distortion of
measurements increasing the farther you get from the center. Another factor is that of the platen against which the
film is pressed can cause severe errors when photographs are used to measure ground distances. The step in which
this problem is resolved is called georeferencing, and involves computer-aided matching up of points in the image
(typically 30 or more points per image) which is extrapolated with the use of an established benchmark, "warping"
the image to produce accurate spatial data. As of the early 1990s, most satellite images are sold fully georeferenced.
In addition, images may need to be radiometrically and atmospherically corrected.
Radiometric correction
gives a scale to the pixel values, e.g. the monochromatic scale of 0 to 255 will be converted to actual radiance
values.
Atmospheric correction
eliminates atmospheric haze by rescaling each frequency band so that its minimum value (usually realised in
water bodies) corresponds to a pixel value of 0. The digitizing of data also make possible to manipulate the
data by changing gray-scale values.
Interpretation is the critical process of making sense of the data. The first application was that of aerial photographic
collection which used the following process; spatial measurement through the use of a light table in both
conventional single or stereographic coverage, added skills such as the use of photogrammetry, the use of
photomosaics, repeat coverage, Making use of objects' known dimensions in order to detect modifications. Image
Analysis is the recently developed automated computer-aided application which is in increasing use.
Object-Based Image Analysis (OBIA) is a sub-discipline of GIScience devoted to partitioning remote sensing (RS)
imagery into meaningful image-objects, and assessing their characteristics through spatial, spectral and temporal
scale.
Old data from remote sensing is often valuable because it may provide the only long-term data for a large extent of
geography. At the same time, the data is often complex to interpret, and bulky to store. Modern systems tend to store
the data digitally, often with lossless compression. The difficulty with this approach is that the data is fragile, the
format may be archaic, and the data may be easy to falsify. One of the best systems for archiving data series is as
computer-generated machine-readable ultrafiche, usually in typefonts such as OCR-B, or as digitized half-tone
images. Ultrafiches survive well in standard libraries, with lifetimes of several centuries. They can be created,
copied, filed and retrieved by automated systems. They are about as compact as archival magnetic media, and yet
can be read by human beings with minimal, standardized equipment.

Remote sensing 71

Data processing levels
To facilitate the discussion of data processing in practice, several processing “levels” were first defined in 1986 by
NASA as part of its Earth Observing System [3] and steadily adopted since then, both internally at NASA (e.g., [4] )
and elsewhere (e.g., [5] ); these definitions are:

Level Description

0 Reconstructed, unprocessed instrument and payload data at full resolution, with any and all communications artifacts (e.g., synchronization
frames, communications headers, duplicate data) removed.

1a Reconstructed, unprocessed instrument data at full resolution, time-referenced, and annotated with ancillary information, including
radiometric and geometric calibration coefficients and georeferencing parameters (e.g., platform ephemeris) computed and appended but not
applied to the Level 0 data (or if applied, in a manner that level 0 is fully recoverable from level 1a data).

1b Level 1a data that have been processed to sensor units (e.g., radar backscatter cross section, brightness temperature, etc.); not all instruments
have Level 1b data; level 0 data is not recoverable from level 1b data.

2 Derived geophysical variables (e.g., ocean wave height, soil moisture, ice concentration) at the same resolution and location as Level 1
source data.

3 Variables mapped on uniform space-time grid scales, usually with some completeness and consistency (e.g., missing points interpolated,
complete regions mosaicked together from multiple orbits, etc).

4 Model output or results from analyses of lower level data (i.e., variables that were not measured by the instruments but instead are derived
from these measurements).

A Level 1 data record is the most fundamental (i.e., highest reversible level) data record that has significant scientific
utility, and is the foundation upon which all subsequent data sets are produced. Level 2 is the first level that is
directly usable for most scientific applications; its value is much greater than the lower levels. Level 2 data sets tend
to be less voluminous than Level 1 data because they have been reduced temporally, spatially, or spectrally. Level 3
data sets are generally smaller than lower level data sets and thus can be dealt with without incurring a great deal of
data handling overhead. These data tend to be generally more useful for many applications. The regular spatial and
temporal organization of Level 3 datasets makes it feasible to readily combine data from different sources.

History
Beyond the primitive methods of remote sensing our earliest ancestors
used (ex.: standing on a high cliff or tree to view the landscape), the
modern discipline arose with the development of flight. The balloonist
G. Tournachon (alias Nadar) made photographs of Paris from his
balloon in 1858. Messenger pigeons, kites, rockets and unmanned
balloons were also used for early images. With the exception of
balloons, these first, individual images were not particularly useful for
map making or for scientific purposes. The TR-1 reconnaissance/surveillance aircraft.

Systematic aerial photography was developed for military surveillance
and reconnaissance purposes beginning in World War I and reaching a climax during the Cold War with the use of
modified combat aircraft such as the P-51, P-38, RB-66 and the F-4C, or specifically designed collection platforms
such as the U2/TR-1, SR-71, A-5 and the OV-1 series both in overhead and stand-off collection. A more recent
development is that of increasingly smaller sensor pods such as those used by law enforcement and the military, in
both manned and

Remote sensing 72

unmanned platforms. The advantage of this approach is that this
requires minimal modification to a given airframe. Later imaging
technologies would include Infra-red, conventional, doppler and
synthetic aperture radar.
The development of artificial satellites in the latter half of the 20th
century allowed remote sensing to progress to a global scale as of the
end of the Cold War. Instrumentation aboard various Earth observing
and weather satellites such as Landsat, the Nimbus and more recent
missions such as RADARSAT and UARS provided global
measurements of various data for civil, research, and military purposes. The 2001 Mars Odyssey used spectrometers and
Space probes to other planets have also provided the opportunity to imagers to hunt for evidence of past or present
water and volcanic activity on Mars.
conduct remote sensing studies in extraterrestrial environments,
synthetic aperture radar aboard the Magellan spacecraft provided
detailed topographic maps of Venus, while instruments aboard SOHO allowed studies to be performed on the Sun
and the solar wind, just to name a few examples.

Recent developments include, beginning in the 1960s and 1970s with the development of image processing of
satellite imagery. Several research groups in Silicon Valley including NASA Ames Research Center, GTE and ESL
Inc. developed Fourier transform techniques leading to the first notable enhancement of imagery data.
The introduction of online web services for easy access to remote sensing data in the 21st century (mainly
low/medium-resolution images), like Google Earth, has made remote sensing more familiar to the big public and has
popularized the science.

Remote Sensing software
Remote Sensing data is processed and analyzed with computer software, known as a remote sensing application. A
large number of proprietary and open source applications exist to process remote sensing data. According to an
NOAA Sponsored Research by Global Marketing Insights, Inc. the most used applications among Asian academic
groups involved in remote sensing are as follows: ERDAS 36% (ERDAS IMAGINE 25% & ERMapper 11%); ESRI
30%; ITT Visual Information Solutions ENVI 17%; MapInfo 17%. Among Western Academic respondents as
follows: ESRI 39%, ERDAS IMAGINE 27%, MapInfo 9%, AutoDesk 7%, ITT Visual Information Solutions ENVI
17%. Other important Remote Sensing Software packages include PCI Geomatics who makes PCI Geomatica, the
leading remote sensing software package in Canada, IDRISI from Clark Labs, and the original object based image
analysis software eCognition from Definiens. Dragon/ips is one of the oldest remote sensing packages still available,
and is in some cases free. Open source remote sensing software includes GRASS GIS, QGIS, OSSIM, Opticks
(software) and Orfeo toolbox.

See also

Remote sensing 73

• Aerial photography • List of Earth observation satellites
• Airborne Real-time Cueing Hyperspectral Enhanced Reconnaissance • Multispectral pattern recognition
• Agricultural Camera • National Center for Remote Sensing, Air, and Space Law
• Archaeological imagery • National LIDAR Dataset
• Cartography • Orthophoto
• CLidar • Pictometry
• Coastal management • Sonar
• Full Spectral Imaging • Radar
• Weather radar
• Geographic information system (GIS) • Radiometry
• Geoinformatics • Remote sensing (archaeology)
• Geophysical survey • Satellite
• Global Positioning System (GPS) • Space probe
• Hyperspectral • Vector Map
[6] • TopoFlight
• IEEE Geoscience and Remote Sensing
• Imagery Analysis
• Imaging Science
• Land cover
• Lidar

Further reading
• Campbell, J.B. (2002). Introduction to remote sensing (3rd ed.). The Guilford Press. ISBN 1-57230-640-8.
• Jensen, J.R. (2007). Remote sensing of the environment: an Earth resource perspective (2nd ed.). Prentice Hall.
ISBN 0-13-188950-8.
• Jensen, J.R. (2005). Digital Image Processing: a Remote Sensing Perspective (3rd ed.). Prentice Hall.
• Lentile, Leigh B.; Holden, Zachary A.; Smith, Alistair M. S.; Falkowski, Michael J.; Hudak, Andrew T.; Morgan,
Penelope; Lewis, Sarah A.; Gessler, Paul E.; Benson, Nate C.. Remote sensing techniques to assess active fire
characteristics and post-fire effects [7]. International Journal of Wildland Fire. 2006;3(15):319-345.
• Lillesand, T.M.; R.W. Kiefer, and J.W. Chipman (2003). Remote sensing and image interpretation (5th ed.).
Wiley. ISBN 0-471-15227-7.
• Richards, J.A.; and X. Jia (2006). Remote sensing digital image analysis: an introduction (4th ed.). Springer.
ISBN 3-540-25128-6.
• US Army FM series.
• US Army military intelligence museum, FT Huachuca, AZ

External links
• Remote Sensing [8] at the Open Directory Project

References
[1] (http:/ / hurricanes. nasa. gov/ earth-sun/ technology/ remote_sensing. html)
[2] Begni Gérard, Escadafal Richard, Fontannaz Delphine and Hong-Nga Nguyen Anne-Thérèse, 2005. Remote sensing: a tool to monitor and
assess desertification. Les dossiers thématiques du CSFD. Issue 2. 44 pp. (http:/ / www. csf-desertification. org/ index. php/ bibliotheque/
publications-csfd/ doc_details/ 28-begni-gerard-et-al-2005-remote-sensing)
[3] NASA (1986), Report of the EOS data panel, Earth Observing System, Data and Information System, Data Panel Report, Vol. IIa., NASA
Technical Memorandum 87777, June 1986, 62 pp. Available at (http:/ / hdl. handle. net/ 2060/ 19860021622)
[4] C. L. Parkinson, A. Ward, M. D. King (Eds.) Earth Science Reference Handbook -- A Guide to NASA’s Earth Science Program and Earth
Observing Satellite Missions, National Aeronautics and Space Administration Washington, D.C. Available at (http:/ / eospso. gsfc. nasa. gov/

Remote sensing 74

ftp_docs/ 2006ReferenceHandbook. pdf)
[5] GRAS-SAF (2009), Product User Manual, GRAS Satellite Application Facility, Version 1.2.1, 31 March 2009. Available at (http:/ / www.
grassaf. org/ general-documents/ products/ grassaf_pum_v121. pdf)
[6] http:/ / www. grss-ieee. org
[7] http:/ / www. treesearch. fs. fed. us/ pubs/ 24613
[8] http:/ / www. dmoz. org/ Science/ Earth_Sciences/ Geomatics/ Remote_Sensing/

Medical imaging
Medical imaging is the technique and process used to create images of the human body (or parts and function
thereof) for clinical purposes (medical procedures seeking to reveal, diagnose or examine disease) or medical science
(including the study of normal anatomy and physiology). Although imaging of removed organs and tissues can be
performed for medical reasons, such procedures are not usually referred to as medical imaging, but rather are a part
of pathology.
As a discipline and in its widest sense, it is part of biological imaging and incorporates radiology (in the wider
sense), nuclear medicine, investigative radiological sciences, endoscopy, (medical) thermography, medical
photography and microscopy (e.g. for human pathological investigations).
Measurement and recording techniques which are not primarily designed to produce images, such as
electroencephalography (EEG), magnetoencephalography (MEG), Electrocardiography (EKG) and others, but which
produce data susceptible to be represented as maps (i.e. containing positional information), can be seen as forms of
medical imaging.

Overview
In the clinical context, medical imaging is generally equated to radiology or "clinical imaging" and the medical
practitioner responsible for interpreting (and sometimes acquiring) the images is a radiologist. Diagnostic
radiography designates the technical aspects of medical imaging and in particular the acquisition of medical images.
The radiographer or radiologic technologist is usually responsible for acquiring medical images of diagnostic
quality, although some radiological interventions are performed by radiologists. While radiology is an evaluation of
anatomy, nuclear medicine provides functional assessment.
As a field of scientific investigation, medical imaging constitutes a sub-discipline of biomedical engineering,
medical physics or medicine depending on the context: Research and development in the area of instrumentation,
image acquisition (e.g. radiography), modelling and quantification are usually the preserve of biomedical
engineering, medical physics and computer science; Research into the application and interpretation of medical
images is usually the preserve of radiology and the medical sub-discipline relevant to medical condition or area of
medical science (neuroscience, cardiology, psychiatry, psychology, etc) under investigation. Many of the techniques
developed for medical imaging also have scientific and industrial applications.
Medical imaging is often perceived to designate the set of techniques that noninvasively produce images of the
internal aspect of the body. In this restricted sense, medical imaging can be seen as the solution of mathematical
inverse problems. This means that cause (the properties of living tissue) is inferred from effect (the observed signal).
In the case of ultrasonography the probe consists of ultrasonic pressure waves and echoes inside the tissue show the
internal structure. In the case of projection radiography, the probe is X-ray radiation which is absorbed at different
rates in different tissue types such as bone, muscle and fat.

Medical imaging 75

Imaging technology

Radiography
Two forms of radiographic images are in use in medical imaging; projection radiography and fluoroscopy, with the
latter being useful for intraoperative and catheter guidance. These 2D techniques are still in wide use despite the
advance of 3D tomography due to the low cost, high resolution, and depending on application, lower radiation
dosages. This imaging modality utilizes a wide beam of x rays for image acquisition and is the first imaging
technique available in modern medicine.
• Fluoroscopy produces real-time images of internal structures of the body in a similar fashion to radiography, but
employs a constant input of x-rays, at a lower dose rate. Contrast media, such as barium, iodine, and air are used
to visualize internal organs as they work. Fluoroscopy is also used in image-guided procedures when constant
feedback during a procedure is required. An image receptor is required to convert the radiation into an image after
it has passed through the area of interest. Early on this was a fluorescing screen, which gave way to an Image
Amplifier (IA) which was a large vacuum tube that had the receiving end coated with cesium iodide, and a mirror
at the opposite end. Eventually the mirror was replaced with a TV camera.
• Projectional radiographs, more commonly known as x-rays, are often used to determine the type and extent of a
fracture as well as for detecting pathological changes in the lungs. With the use of radio-opaque contrast media,
such as barium, they can also be used to visualize the structure of the stomach and intestines - this can help
diagnose ulcers or certain types of colon cancer.

Magnetic resonance imaging (MRI)
A magnetic resonance imaging instrument (MRI scanner), or "nuclear
magnetic resonance (NMR) imaging" scanner as it was originally
known, uses powerful magnets to polarise and excite hydrogen nuclei
(single proton) in water molecules in human tissue, producing a
detectable signal which is spatially encoded, resulting in images of the
body. MRI uses three electromagnetic fields: a very strong (on the
order of units of teslas) static magnetic field to polarize the hydrogen
nuclei, called the static field; a weaker time-varying (on the order of
1 kHz) field(s) for spatial encoding, called the gradient field(s); and a
weak radio-frequency (RF) field for manipulation of the hydrogen
nuclei to produce measurable signals, collected through an RF antenna.

Like CT, MRI traditionally creates a two dimensional image of a thin
"slice" of the body and is therefore considered a tomographic imaging
technique. Modern MRI instruments are capable of producing images
in the form of 3D blocks, which may be considered a generalisation of
A brain MRI representation
the single-slice, tomographic, concept. Unlike CT, MRI does not
involve the use of ionizing radiation and is therefore not associated
with the same health hazards. For example, because MRI has only been in use since the early 1980s, there are no
known long-term effects of exposure to strong static fields (this is the subject of some debate; see 'Safety' in MRI)
and therefore there is no limit to the number of scans to which an individual can be subjected, in contrast with X-ray
and CT. However, there are well-identified health risks associated with tissue heating from exposure to the RF field
and the presence of implanted devices in the body, such as pace makers. These risks are strictly controlled as part of
the design of the instrument and the scanning protocols used.

Medical imaging 76

Because CT and MRI are sensitive to different tissue properties, the appearance of the images obtained with the two
techniques differ markedly. In CT, X-rays must be blocked by some form of dense tissue to create an image, so the
image quality when looking at soft tissues will be poor. In MRI, while any nucleus with a net nuclear spin can be
used, the proton of the hydrogen atom remains the most widely used, especially in the clinical setting, because it is
so ubiquitous and returns a large signal. This nucleus, present in water molecules, allows the excellent soft-tissue
contrast achievable with MRI.

Nuclear medicine
Nuclear medicine encompasses both diagnostic imaging and treatment of disease, and may also be referred to as
molecular medicine or molecular imaging & therapeutics [1] . Nuclear medicine uses certain properties of isotopes
and the energetic particles emitted from radioactive material to diagnose or treat various pathology. Different from
the typical concept of anatomic radiology, nuclear medicine enables assessment of physiology. This function-based
approach to medical evaluation has useful applications in most subspecialties, notably oncology, neurology, and
cardiology. Gamma cameras are used in e.g. scintigraphy, SPECT and PET to detect regions of biologic activity that
may be associated with disease. Relatively short lived isotope, such as 123I is administered to the patient. Isotopes
are often preferentially absorbed by biologically active tissue in the body, and can be used to identify tumors or
fracture points in bone. Images are acquired after collimated photons are detected by a crystal that gives off a light
signal, which is in turn amplified and converted into count data.
• Scintigraphy ("scint") is a form of diagnostic test wherein radioisotopes are taken internally, for example
intravenously or orally. Then, gamma camera capture and form two-dimensional[2] images from the radiation
emitted by the radiopharmaceuticals.
• SPECT is a 3D tomographic technique that uses gamma camera data from many projections and can be
reconstructed in different planes. A dual detector head gamma camera combined with a CT scanner, which
provides localization of functional SPECT data, is termed a SPECT/CT camera, and has shown utility in
advancing the field of molecular imaging.
• Positron emission tomography (PET) uses coincidence detection to image functional processes. Short-lived
positron emitting isotope, such as 18F, is incorporated with an organic substance such as glucose, creating
F18-fluorodeoxyglucose, which can be used as a marker of metabolic utilization. Images of activity distribution
throughout the body can show rapidly growing tissue, like tumor, metastasis, or infection. PET images can be
viewed in comparison to computed tomography scans to determine an anatomic correlate. Modern scanners
combine PET with a CT, or even MRI, to optimize the image reconstruction involved with positron imaging. This
is performed on the same equipment without physically moving the patient off of the gantry. The resultant hybrid
of functional and anatomic imaging information is a useful tool in non-invasive diagnosis and patient
management.

Photoacoustic imaging
Photoacoustic imaging is a recently developed hybrid biomedical imaging modality based on the photoacoustic
effect. It combines the advantages of optical absorption contrast with ultrasonic spatial resolution for deep imaging
in (optical) diffusive or quasi-diffusive regime. Recent studies have shown that photoacoustic imaging can be used in
vivo for tumor angiogenesis monitoring, blood oxygenation mapping, functional brain imaging, and skin melanoma
detection, etc.

Medical imaging 77

Breast Thermography
Digital infrared imaging thermography is based on the principle that metabolic activity and vascular circulation in
both pre-cancerous tissue and the area surrounding a developing breast cancer is almost always higher than in normal
breast tissue. Cancerous tumors require an ever-increasing supply of nutrients and therefore increase circulation to
their cells by holding open existing blood vessels, opening dormant vessels, and creating new ones
(neoangiogenesis). This process frequently results in an increase in regional surface temperatures of the breast.
Digital infrared imaging uses extremely sensitive medical infrared cameras and sophisticated computers to detect,
analyze, and produce high-resolution diagnostic images of these temperature variations. Because of DII's sensitivity,
these temperature variations may be among the earliest signs of breast cancer and/or a pre-cancerous state of the
breast[3] .

Tomography
Tomography is the method of imaging a single plane, or slice, of an object resulting in a tomogram. There are
several forms of tomography:
• Linear tomography: This is the most basic form of tomography. The X-ray tube moved from point "A" to point
"B" above the patient, while the cassette holder (or "bucky") moves simultaneously under the patient from point
"B" to point "A." The fulcrum, or pivot point, is set to the area of interest. In this manner, the points above and
below the focal plane are blurred out, just as the background is blurred when panning a camera during exposure.
No longer carried out and replaced by computed tomography.
• Poly tomography: This was a complex form of tomography. With this technique, a number of geometrical
movements were programmed, such as hypocycloidic, circular, figure 8, and elliptical. Philips Medical Systems
[4] produced one such device called the 'Polytome.' This unit was still in use into the 1990s, as its resulting
images for small or difficult physiology, such as the inner ear, was still difficult to image with CTs at that time.
As the resolution of CTs got better, this procedure was taken over by the CT.
• Zonography: This is a variant of linear tomography, where a limited arc of movement is used. It is still used in
some centres for visualising the kidney during an intravenous urogram (IVU).
• Orthopantomography (OPT or OPG): The only common tomographic examination in use. This makes use of a
complex movement to allow the radiographic examination of the mandible, as if it were a flat bone. It is often
referred to as a "Panorex", but this is incorrect, as it is a trademark of a specific company.
• Computed Tomography (CT), or Computed Axial Tomography (CAT: A CT scan, also known as a CAT scan, is
a helical tomography (latest generation), which traditionally produces a 2D image of the structures in a thin
section of the body. It uses X-rays. It has a greater ionizing radiation dose burden than projection radiography;
repeated scans must be limited to avoid health effects.

Ultrasound
Medical ultrasonography uses high frequency broadband sound waves in the megahertz range that are reflected by
tissue to varying degrees to produce (up to 3D) images. This is commonly associated with imaging the fetus in
pregnant women. Uses of ultrasound are much broader, however. Other important uses include imaging the
abdominal organs, heart, breast, muscles, tendons, arteries and veins. While it may provide less anatomical detail
than techniques such as CT or MRI, it has several advantages which make it ideal in numerous situations, in
particular that it studies the function of moving structures in real-time, emits no ionizing radiation, and contains
speckle that can be used in elastography. It is very safe to use and does not appear to cause any adverse effects,
although information on this is not well documented. It is also relatively inexpensive and quick to perform.
Ultrasound scanners can be taken to critically ill patients in intensive care units, avoiding the danger caused while
moving the patient to the radiology department. The real time moving image obtained can be used to guide drainage
and biopsy procedures. Doppler capabilities on modern scanners allow the blood flow in arteries and veins to be

Medical imaging 78

assessed.

Medical imaging topics

Maximizing imaging procedure use
The amount of data obtained in a single MR or CT scan is very extensive. Some of the data that radiologists discard
could save patients time and money, while reducing their exposure to radiation and risk of complications from
invasive procedures.[4]

Creation of three-dimensional images
Recently, techniques have been developed to enable CT, MRI and ultrasound scanning software to produce 3D
images for the physician.[5] Traditionally CT and MRI scans produced 2D static output on film. To produce 3D
images, many scans are made, then combined by computers to produce a 3D model, which can then be manipulated
by the physician. 3D ultrasounds are produced using a somewhat similar technique. In diagnosing disease of the
viscera of abdomen,ultrasound is particularly sensitive on imaging of biliary tract,urinary tract and female
reproductive organs(ovary,fallopian tubes).As for example,diagnosis of gall stone by dilatation of common bile duct
and stone in common bile duct . With the ability to visualize important structures in great detail, 3D visualization
methods are a valuable resource for the diagnosis and surgical treatment of many pathologies. It was a key resource
for the famous, but ultimately unsuccessful attempt by Singaporean surgeons to separate Iranian twins Ladan and
Laleh Bijani in 2003. The 3D equipment was used previously for similar operations with great success.
Other proposed or developed techniques include:
• Diffuse optical tomography
• Elastography
• Electrical impedance tomography
• Optoacoustic imaging
• Ophthalmology
• A-scan
• B-scan
• Corneal topography
• Optical coherence tomography
• Scanning laser ophthalmoscopy
Some of these techniques are still at a research stage and not yet used in clinical routines.

Compression of medical images
Medical imaging techniques produce very large amounts of data, especially from CT, MRI and PET modalities. As a
result, storage and communications of electronic image data are prohibitive without the use of compression. JPEG
2000 is the state-of-the-art image compression DICOM standard for storage and transmission of medical images.
The cost and feasibility of accessing large image data sets over low or various bandwidths are further addressed by
use of another DICOM standard, called JPIP, to enable efficient streaming of the JPEG 2000 compressed image data.

Medical imaging 79

Non-diagnostic imaging
Neuroimaging has also been used in experimental circumstances to allow people (especially disabled persons) to
control outside devices, acting as a brain computer interface.

Archiving and recording
Used primarily in ultrasound imaging, capturing the image a medical imaging device is required for archiving and
telemedicine applications. In most scenarios, a frame grabber is used in order to capture the video signal from the
medical device and relay it to a computer for further processing and operations.[6]

Open source software for medical image analysis
Several open source software packages are available for performing analysis of medical images:
• ImageJ
• 3D Slicer
• ITK
• OsiriX
• GemIdent
• MicroDicom
• FreeSurfer
• FreePlugin

Use in pharmaceutical clinical trials
Medical imaging has become a major tool in clinical trials since it enables rapid diagnosis with visualization and
quantitative assessment.
A typical clinical trial goes through multiple phases and can take up to eight years. Clinical endpoints or outcomes
are used to determine whether the therapy is safe and effective. Once a patient reaches the endpoint, he/she is
generally excluded from further experimental interaction. Trials that rely solely on clinical endpoints are very costly
as they have long durations and tend to need large number of patients.
In contrast to clinical endpoints, surrogate endpoints have been shown to cut down the time required to confirm
whether a drug has clinical benefits. Imaging biomarkers (a characteristic that is objectively measured by an imaging
technique, which is used as an indicator of pharmacological response to a therapy) and surrogate endpoints have
shown to facilitate the use of small group sizes, obtaining quick results with good statistical power.[7]
Imaging is able to reveal subtle change that is indicative of the progression of therapy that may be missed out by
more subjective, traditional approaches. Statistical bias is reduced as the findings are evaluated without any direct
patient contact.
For example, measurement of tumour shrinkage is a commonly used surrogate endpoint in solid tumour response
evaluation. This allows for faster and more objective assessment of the effects of anticancer drugs. In evaluating the
extent of Alzheimer’s disease, it is still prevalent to use behavioural and cognitive tests. MRI scans on the entire
brain can accurately pinpoint hippocampal atrophy rate while PET scans is able to measure the brain’s metabolic
activity by measuring regional glucose metabolism.[7]
An imaging-based trial will usually be made up of three components:
1. A realistic imaging protocol. The protocol is an outline that standardizes (as far as practically possible) the way in
which the images are acquired using the various modalities (PET, SPECT, CT, MRI). It covers the specifics in
which images are to be stored, processed and evaluated.
2. An imaging centre that is responsible for collecting the images, perform quality control and provide tools for data
storage, distribution and analysis. It is important for images acquired at different time points are displayed in a

Medical imaging 80

standardised format to maintain the reliability of the evaluation. Certain specialised imaging contract research
organizations provide to end medical imaging services, from protocol design and site management through to data
quality assurance and image analysis.
3. Clinical sites that recruit patients to generate the images to send back to the imaging centre.

See also
• Preclinical imaging • Magnetic field imaging • Pneumoencephalogram
• Cardiac PET • Medical examination • Radiology information system
• Biomedical informatics • Medical radiography • Segmentation (image processing)
• Digital Imaging and Communications in • Medical test • Signal-to-noise ratio
Medicine
• Digital Mammography and PACS • Neuroimaging • Society for Imaging Science and Technology
• EMMI European Master in Molecular Imaging • Non-invasive (medical) • Tomogram
• Fotofinder • PACS • Virtopsy
• Full-body scan • JPEG 2000
compression
• VoluMedic • JPIP streaming

Further reading
• Burger, Wilhelm; Burge, Mark James, eds (2008). Digital Image Processing: An Algorithmic Introduction using
Java. Texts in Computer Science series. New York: Springer Science+Business Media.
doi:10.1007/978-1-84628-968-2. ISBN 978-1-84628-379-6.
• Baert, Albert L., ed (2008). Encyclopedia of Diagnostic Imaging. Berlin: Springer-Verlag.
doi:10.1007/978-3-540-35280-8. ISBN 978-3-540-35278-5.
• Tony F. Chan and Jackie Shen (2005). Image Processing and Analysis - Variational, PDE, Wavelet, and
Stochastic Methods [9]. SIAM
• Terry Yoo(Editor) (2004), Insight into Images.
• Robb, RA (1999). Biomedical Imaging, Visualization, and Analysis. John Wiley & Sons, Inc. ISBN 0471283533.
• Journal of Digital Imaging (New York: Springer Science+Business Media). ISSN 0897-1889.
• Using JPIP for Standard-Compliant Sharing of Medical Image Data [10] a white paper by Aware Inc. [11]

External links
• Medical imaging [12] at the Open Directory Project
• Medical Image Database [13] Free Indexed Online Images
• http://www.aware.com/imaging/accuradjpip.htm What is JPIP?

References
[1] Society of Nuclear Medicine (http:/ / www. snm. org)
[2] thefreedictionary.com > scintigraphy (http:/ / medical-dictionary. thefreedictionary. com/ scintigraphy) Citing: Dorland's Medical Dictionary
for Health Consumers, 2007 by Saunders; Saunders Comprehensive Veterinary Dictionary, 3 ed. 2007; McGraw-Hill Concise Dictionary of
Modern Medicine, 2002 by The McGraw-Hill Companies
[3] http:/ / www. breastthermography. com/ breast_thermography_mf. htm
[4] Freiherr G. Waste not, want not: Getting the most from imaging procedures (http:/ / www. diagnosticimaging. com/ news/ display/ article/
113619/ 1541872). Diagnostic Imaging. March 19, 2010.
[5] Udupa, J.K. and Herman, G. T., 3D Imaging in Medicine, 2nd Edition, CRC Press, 2000
[6] Treating Medical Ailments in Real Time (http:/ / www. epiphan. com/ solutions_new/ ?arid=16)
[7] Hajnal, J. V., Hawkes, D. J., & Hill, D. L. (2001). Medical Image Registration. CRC Press.


Article Sources and Contributors
Image Source: http://en.wikipedia.org/w/index.php?oldid=362345169 Contributors: $dollarz$, *drew, A bit iffy, Aapo Laitinen, Aaron DT, Academic Challenger, Accurizer, AdjustShift,
Adoniscik, Adrian, Aek3755, Ahoerstemeier, Aitias, Aitsukai, Alansohn, Alex S, Alexius08, Altenmann, Altermike, Amog, Anamc60, Anas Salloum, Anaxial, Anclation, Andycjp, Anirvan, Ann
Stouter, Anonymous editor, Antipastor, Arachnidkid123, Ariaconditzione, Arjun01, ArnoldReinhold, Arslion, Arthur Rubin, Astroview120mm, AxelBoldt, Baboshed, Baloonga, Bardak,
Bbb00723, Bevo, Bhteam, Bigbluefish, Billbouchard, BillyMInScience, Blanchardb, BluesD, Bob98133, Bonadea, BryanG, Btaysisson, Bubblesroo, Bumphoney, CQJ, Caknuck, Calliopejen1,
Caltas, Can't sleep, clown will eat me, Capsal, Captain Weirdo the Great, Carnildo, Ccacsmss, Cdimage, Chanman, Charlesdrakew, Chase me ladies, I'm the Cavalry, Cheyennedoesntpickernose,
Chronomantic, Chzz, Cometstyles, Conti, Cryptic, Cryptoid, Cureden, Curtis, Cybercobra, DMacks, DVD R W, Daediter12345, Dainis, Daniil Maslyuk, Dave souza, Db099221, Deathgecko,
Deconstructhis, Demiurge, DennisDaniels, Derek Ross, Deville, Dicklyon, Disambiguator, Discospinster, DocWatson42, Doomed Rasher, Drake the dragon, Drini, Dysprosia, Ed Fitzgerald,
Edgar181, Elroch, Epbr123, Erudecorp, Everyking, Evil Monkey, Ezekiel 7:19, Faradayplank, Fastilysock, Fennec, Feureau, Fox, Francisx, FreplySpang, GB fan, GDonato, Gaped, Gary134,
Gavroche42, Gio717, Gioj50, Giraffedata, Gogo Dodo, Gotox, GraemeL, Grafikm fr, GrahamN, Grape, Greg, Grutness, Gscshoyru, Guesswhosback121, Gurch, Gyro Copter, Haakon,
HaboFreakNumber2, Hadal, Happyhug1, Harriv, Haukurth, Haunti, Hede2000, Hera1187, Hetar, Howdoesthiswo, Hut 8.5, Huzefahamid, I rox @ 13, ICGC software technologies, IRP,
IShadowed, Igiffin, Indianofficebuildings, Indon, Isnow, J.delanoy, J04n, James.kendall, Jeepday, Jeff G., Jeffq, JeremyA, JetLover, Jicard, Jiddisch, JohnCD, JohnOwens, Jorge Stolfi, Jossi,
Jrugordon, Jseamen, Jshadias, JuWiki, KTo288, Kablammo, Kainaw, Kajasudhakarababu, Kansan, Kgasso, King of Hearts (old account 2), Kingpin13, Kjramesh, Kleptosquirrel, La goutte de
pluie, Lars Washington, Lazylaces, Leafyplant, Lelkesa, Leonardmrija82, Leuko, Linjr32, Lithoderm, LittleOldMe, LobStoR, LoggedInWiki, LordMooCow, Lozeldafan, Lradrama, Luk, Luna
Santin, Lycurgus1920, M0lliEEM, MER-C, Magnus Manske, Malo, Maralia, MarcellRowe, Mario12184, MarkS, Martarius, Mastrchf91, Mattbl34, Mattiuscn, Maxis ftw, Michael Hardy, Mifter,
Mikebrands, Mintleaf, Modernist, MrOllie, Munita Prasad, MusicCyborg23, N5iln, NERIC-Security, Nathaliecatcats, NeilN, Nestea Zen, Nickcasey10, Nihil novi, Nordanjordan, Norvy,
NuclearWarfare, OEMCUST, Oicumayberight, Olaf Simons, Ossmann, PAR, PEPSI2K7, PGSONIC, Patlittle, Patrick, PatrickFlaherty, Pavel Vozenilek, Pekaje, Perl, Pgarwood, Pgreenfinch,
Phatsphere, Phys, Piano non troppo, Pile3d, Pilotguy, Plantsurfer, Pojanji, Pol098, Polysillycon, Possum, Prodego, Punckitty, Purplecows123, Quailman, Qwerqewrqew, Qxz, RJaguar3, Rachdi,
Radon210, Reinhardheydt, Reinyday, Research Method, Rettetast, Riana, Roleplayer, Ronhjones, Ronz, Roxyluver, Royboycrashfan, Ryanrocker, Rybioko, Ryulong, S, SJP, Sairen42,
SchfiftyThree, ScottJ, Shanes, Shoessss, Shulian, SimonP, Singboyb16, Skeetch, Skew-t, Smack, SmthManly, SnowFire, Snowolf, Soliloquial, Someoneddd, Songsmail, Spitfire, Srleffler,
Stephen, Stephenchou0722, Stevertigo, Styrofoam1994, SunDragon34, Sundaramsahnee, Sunroof, Superm401, THEN WHO WAS PHONE?, TJDay, Tao of tyler, Tenebrae, TexasAndroid, The
Evil Spartan, The New iPod., The Rambling Man, The Thing That Should Not Be, The V.A.N.D.A.L. Man, TheEgyptian, TheKMan, TheMindsEye, Theonenow, Thisisborin9, Thruston,
Thudrs1, Thunderhippo, Toby Bartels, Tom scaret1284564, Tomg-unit, Trampledtown, Treisijs, TutterMouse, Tyrenius, UdovdM, Ufim, Umerfaroo q, Uncle Dick, Valerian456, Vipinhari,
Vsmith, WAvegetarian, WadeSimMiser, Wapcaplet, Wayiran, Weeliljimmy, Wernher, Werratal, Wetman, Whosyourjudas, Wiki alf, Wikibofh, Wikidudeman, Wikiwiki, Wimt, Wknight94,
Woohookitty, Wshun, Yamamoto Ichiro, Yekrats, Yidisheryid, Ykhwong, Yosufimas229, Zephyris, Zvn, 547 anonymous edits

Pixel Source: http://en.wikipedia.org/w/index.php?oldid=364019851 Contributors: -Majestic-, A9gould1, AGToth, Aditya, AdjustShift, Agateller, Agentbla, Aggsal, Ahoerstemeier,
Akhilhello6, Aldie, Alex43223, Ali, Amniarix, Anclation, Andreas Kaufmann, Andrevan, AndrewWTaylor, Andrewpmk, Andries, Angus Lepper, Ap, Ariedartin, Arny, Arpingstone, Askewchan,
Astronouth7303, Atchius, Atif.t2, Auntof6, AxG, BarretBonden, Barsoomian, Basu, Bazza1971, Bearcat, Bedelato, Bender235, Betacommand, BiT, Binba, Bit, Blahma, Bobo192, Bookofjude,
Bornhj, Brandt Luke Zorn, Bricevdm, Brockert, Bubba hotep, C0nanPayne, Caltas, Can't sleep, clown will eat me, Catgut, CelticJobber, Centrx, Chensiyuan, Chsimps, Closedmouth, Conversion
script, Cryptic, Da monster under your bed, Dante Alighieri, Dave3457, Davepape, David Levy, Dbenbenn, Dcljr, Dennis Valeev, DerHexer, Dhatfield, Dicklyon, Discospinster, Dmmaus,
Dogsthatchasecars, Donarreiskoffer, Dosnerd90, Doug Bell, Dreg743, ESkog, Ed g2s, Edward, ElGordo, Electron9, Eliz81, Elkman, Ellmist, Ellywa, Enos Shenk, Epbr123, Erik9, Ethaniscool1,
FCYTravis, Fastfission, Ferengi, Feydey, FiP, Firsfron, Fishnet37222, Fleminra, Flewis, ForestJay, Frecklefoot, Fritz Jörn, Fuhghettaboutit, Fusionmix, Gaius Cornelius, Galoubet, Gbrugman,
Georgec, Ghakko, Ghewgill, Giftlite, Gits (Neo), Gogo Dodo, Graham87, Guppy, Gurubrahma, Haakon, Hadal, Haham hanuka, Hamish2k, Handy helper, Haseo9999, Hephaestos, Heracles31,
Heron, Hfastedge, Hkpawn, Imroy, Ioapetraka, Ixfd64, J.delanoy, JIP, Janke, JayJayKay, Jeff G., Jeffrey O. Gustafson, Jfingers88, Jim.henderson, JuanFox, Juliancolton, Karada, Kbdank71,
Keenan Pepper, Keilana, Kieff, Kim Bruning, Kim0kim0, Kirill Lokshin, Kjkolb, Kjlewis, Kpjas, Kprateek88, Kwaku, LOL, LarryGilbert, Ld100, Liftarn, Localdara, Lordofthe9, Lumpbucket,
Lysdexia, M.nelson, MARKYSPARKY19, MER-C, Malo, Marasmusine, Mark83, Mattisse, Maxim, Mdd, Merlinme, Merphant, Miaow Miaow, Michael Hardy, Midway, Mikeipedia, Miraceti,
Mlaine, Morken, Moxfyre, MrMambo, Mwhiteguy, NawlinWiki, Necronomicronistic, Nimbusania, Nmacu, Ohnoitsjamie, Omegatron, OnBeyondZebrax, Orderud, Oyd11, Patrick, Pearle, Pengo,
Pete Peterson, Pforret, Philippe, Pilotguy, Pinball22, Pinethicket, Pinkadelica, Pizza Puzzle, Planemad, Poeloq, Preslethe, Prewitt81, Puchiko, Punch, Drunk, Love, Pursin1, Qxz, Qz, Ran4,
Rebornsoldier, RedHillian, Reedbeta, RexNL, Ricky81682, Rob215, Robert Buzink, Rocket000, Rory096, Roux, Ruslik0, SJP, Sabisteven, Sam Korn, Samuell, Samus3456, Santrobi, Sceptre,
Scott McNay, ScriptedGhost, Seabhcan, Seb, Sebleblanc, Secfan, Sergeyy, Shirik, Silver Edge, Simeon, SimonP, SimonPowell, Sionus, Sjanuary, Slokunshialgo, Sluzzelin, Smalljim, SmartAVI,
Snowolf, SouthernMyst, Speck-Made, Srleffler, Staffwaterboy, Sum0, Svick, TAKASUGI Shinji, Tarquin, The wub, TheMindsEye, Thecheesykid, Themepark, This, that and the other, Thw1309,
TimMagic, Tiptoety, Tombomp, Trekphiler, Tuspm, Urdna, Utcursch, VMS Mosaic, Violetriga, Vladsinger, Wapcaplet, Wavelength, Wernher, Wik, Wiki alf, Wikid77, Wikidudeman,
Wtshymanski, Xenoranger, Yekrats, Yudiweb, ZacBowling, Zanimum, Zdog18, ZeroOne, Zlobny, Zundark, Михајло Анђелковић, 508 anonymous edits

Image processing Source: http://en.wikipedia.org/w/index.php?oldid=362347544 Contributors: Abhinav.bal, Abmac, Adoniscik, Alanbly, Andre Engels, Andthu, AndyCharles1Wilson,
Animum, Apyule, Asc99c, Bact, Barticus88, Bravekermit, BrentN, C3o, Calltech, Carloscastro, Cburnett, Chintanbug, Dancter, DanielZhang27, Dicklyon, Dwachter, Dysprosia, EagleFan, Fangz,
Ferengi, Fgnievinski, Finn-Zoltan, Fletch1978, Flightsoffancy, Fordescort79, Giftlite, GillianSmith, HarisM, Hezarfenn, Huotfh, Inschanör, Iobuddha, James086, Jiuguang Wang, Johnuniq,
Jonawebb, Jorge Stolfi, Kamoshirenai, Karol Langner, Kipmaster, Komap, Kutabar, Lamoidfl, Lee Daniel Crocker, Mahogny, Malte singapore, Mani1, Marc Lacoste, Matt Britt, Mdd, Mdd4696,
Meera123, Melaneum, Michael Hardy, MichaelBillington, MightCould, Minghong, Mostafa.elhoushi, Mr Yarrow, MrMambo, Nbarth, Nitin.mehta, Odo1982, Orderud, Organizmo, Ossmann,
PAR, Panecasareccio, Pearle, Phillipsacp, Pollinator, Poor Yorick, Porieu, Predictor, Pvosta, Quuxplusone, Renatokeshet, Requestion, Rholton, Roesser, Sam Korn, Sbowers3, Seabhcan,
SensibleStuff, Smack, Solipsist, Stw, Sumbaug, Supten, The Anome, Theresa knott, Tpl, Tuxide, User A1, Verbal, Wafulz, Waxigloo, Wikipedie, Wipware, Ylloh, Yswismer, 163 anonymous
edits

Digital image processing Source: http://en.wikipedia.org/w/index.php?oldid=361813256 Contributors: 777sms, Abdull, Adoniscik, Alansohn, Alex Spade, Andre Engels, AngelovdS, Apm-gh,
Asc99c, Bact, Barticus88, Beetstra, BrentN, Canaima, Cburnett, Chunawalla, D hanbun, DBAllan, DavidCary, Dchristle, Dicklyon, Dysprosia, Eekerz, Either way, Ekotkie, Enselic, Enviroboy,
Fgnievinski, Flowerheaven, GRAHAMUK, Giftlite, Glogger, HairyWombat, Hermann.tropf, Hezarfenn, Hosse, Imagegod, Inputpersona, Isnow, Jamelan, Jehochman, JimmyTheWig, Jiuguang
Wang, Johnuniq, Jorge Stolfi, Keilana, Lamoidfl, Lbarajas, Ligulem, MER-C, Matt Britt, Mav, Mholland, Michael Hardy, MightCould, Mindmatrix, Mr Yarrow, MrOllie, Naturenet, NawlinWiki,
Nbarth, Nilx, Nmnogueira, Nneonneo, ONEder Boy, Orderud, Pedronavajo, Phillipsacp, Prashantsonar, Predictor, Pvosta, Quuxplusone, Rich Farmbrough, Roesser, Roshan baladhanvi,
Sanfranman59, Sannse, Satishpitchikala, Seabhcan, Shireesh13, Snowolf, Stillastillsfan, Stonor, TFOWR, Targetter, The Anome, Themcman1, Tobias Conradi, Tomkalayil, Tuxide, User A1,
Wharron, Wiki alf, Wikipedie, Wildknot, Yaroslavvb, Ylloh, Zvika, Zvn, ‫ 021 ,اضر.دمحم ,کشرز‬anonymous edits

Optical character recognition Source: http://en.wikipedia.org/w/index.php?oldid=364480171 Contributors: (jarbarf), 119, 7, AaB-ern, Abcde2, Abdull, Affection, Ahlc, Ahoerstemeier, Ahunt,
Alfio, Alfirin, Amoverload, Andrewpmk, Ankit1 nagpal, AramediA, Artemgy, Ashton1983, Asiavision01, Austinmurphy, B, B4hand, Backburner001, Backpackadam, Badly Bradley,
Batmanand, Beetstra, Beland, Ben-Zin, Betterusername, Bisqwit, Bkkbrad, Blanchardb, Blendenzo, Bollinger, Bookofjude, Borgx, Brothaslide, BrotherE, C777, CVISION, Can't sleep, clown
will eat me, CanisRufus, Celithemis, Chowells, Chris 73, Chrisnewell, Christopher Parham, Chrysalis, Cobaltbluetony, ColinMB, Compvis, Conway71, Craigb81, Creidieki, D, D'Artagnol,
Damian Yerrick, Dance1992, DanielZhang27, Dataxprts, David Gerard, DavidCary, Davydog, Dbachmann, Dcoetzee, Deepred6502, Delldot, Den fjättrade ankan, Denelson83, Denoir,
Dhshepard, Diablonhn, Dionyseus, Distantbody, Draney13, Drone007, Dust Filter, Dvidby0, Edwindreillyjr, Eequor, Emersoni, Encephalon, Erwin, Erxnmedia, EtherealPurple, Etincelles,
Euchiasmus, Fernkes, Fireice, Franzvm, Frecklefoot, FreplySpang, Ftiercel, GJo, Gabbe, GeorgeLouis, Gerbrant, Gershwinrb, Gevans712, Gianmarcocastagna, Giftlite, Gmcfoley, Goldencako,
Grstain, Gwalla, Gypsydoctor, Hadal, Hauskalainen, Havarhen, Hike395, Hippietrail, Hm2k, Hulagutten, INkubusse, Iainscott, Iayork, Igmat, Ignacio Javier Igjav, Imroy, Indefatigable, Intgr,
Ivan Akira, J.delanoy, JPG-GR, JTN, James Foster, Jason Quinn, Jbrox, JidGom, Joachimb, John of Reading, Jonas Viper, Josehill, Joshua lee, Jpbowen, Just Another Dan, KYN, Kablammo,
Kallerdis, Kanakukk, Karada, Kaszeta, KellyCoinGuy, Kingpin13, Kiwipat, Kizor, Knucmo2, Kuru, Kyeung123, Kzamir, Lafirel, Lakshmish, Laurusnobilis, Leafyplant, Lee Carre, LjL,
Loveonearth, Luna Santin, M4gnum0n, Mac, Mani1, MariaDR, Marinazhao, MarkAnthony01, Markk474, Martey, Martinlc, Matthias Röder, Matticus78, Mbutts, McGeddon, Miaow Miaow,
MicahDCochran, Michael Hardy, Mickeymousechen, Mindmatrix, Morgan814, Mvcfalcon, Mwtoews, Nakon, Nardyca, NeonMerlin, Netsnipe, Nneonneo, North8000, OCR-PDF, Ohka-,
Orangemike, Orlando7777, OsamaBinLogin, Otaviogood, PMDrive1061, Pablo X, ParsaNikbin, Patrick, PenComputingPerson, Penubag, Peter Winnberg, Peter bertok, Pgdyck, Pierson's
Puppeteer, Pol098, Porthugh, Predictor, Proofreader77, PseudoSudo, PureFire, Pwnvds, Quiggles, RHaworth, Raryel, Raysonho, Reedy, Renesis, Requestion, Rethunk, Rfl, Rhagerman, Rich
Farmbrough, Rick Sidwell, Ricky@36, Rjstott, Rjwilmsi, Rlove, Robert Merkel, Robert.Baruch, Rocastelo, Rompe, Ronz, Rory096, Rwxrwxrwx, Saladinct, Salvadors, Sarregouset, Saxifrage,
ScanStoreAaron, SchuminWeb, Seabhcan, Shadow1, Sharareh 601, Sharnden, ShaunMacPherson, Shoeofdeath, Shyam, Silversmith, Sjakkalle, Slakr, Slham1972, Sligocki, Slike2, Slysplace,
Smile a While, Sonjaaa, Spanthony, SpeedyGonsales, SqueakBox, Stalfur, Stopol, StorkenSture, Sunjan, Superduperpup, Szajd, TWWhiting, Tandras, Tarikash, Tempshill, Terence, TerriersFan,
Tesi1700, The Thing That Should Not Be, Thumperward, Tide rolls, Timwi, TonyClarke, Tosha, Tregoweth, Udayangahpur, Ultimus, UninvitedCompany, User27091, VR718, Vald, Versageek,
Violetriga, Warofdreams, Wernher, Wickedpede, Wiki alf, WikiLyd, Wikinoki, Wimt, Winterdragon, Xfreebird, Xiaofan Lin, Xris0, Yabbadab, Youlivnlearn, Ytterbium3, Yworo,
ZorbaTheSwede, ‫ ,ملاع بوبحم‬चंद्रकांत धुतडमल, 572 anonymous edits

Computer vision Source: http://en.wikipedia.org/w/index.php?oldid=363512096 Contributors: 155.54.12.xxx, 66.24.100.xxx, APH, Aaronh, Ademarius, Ahy1, Albert Chen, Alksub, Ancheta
Wis, Andreas Kaufmann, AndyCharles1Wilson, Art LaPella, Arthena, Awaterl, Az1568, Bact, Bartledan, Beanly, Bensmith, Biscuittin, Bootedcat, Brockert, Bruceporteous, Calltech,
Cantalamessa, Ceosion, Chadloder, Cmdrjameson, Comixboy, Compvis, Compvision, ContiAWB, Conversion script, Correct47, Crispichikin, Czwerling1, Dancter, David Andel, Delaszk,
Devantheryv, Dicklyon, Dishayloo, Doktor, DopefishJustin, Dougthebug, Doze, Dysprosia, Edcolins, Epbr123, Fcummins, Femto, Flightsoffancy, Frap, Freestyle, Fvw, Gaius Cornelius,


Garybradski, Gene s, Gengiskanhg, Giftlite, GillianAnderson, Grimple, Hike395, Hobbes, Hu, Idgs78, Idiap, Iknowyourider, Instantaneous, Isnow, Ivan Štambuk, Jacobsn, JamesCrowley,
Jbhuang, Jcarroll, Jfurr1981, Jhhays, Jiuguang Wang, Johnuniq, Jonjlaw, Jonschlueter, KYN, Kablammo, Kamoshirenai, Kegon, KennanLau, Kimchi.sg, Kozuch, KrakatoaKatie, Kurykh, Kusma,
Labsji, Lbarajas, Lgrove, MER-C, Male1979, Mario1337, Martpol, McLoaf, Mdouze, Mfklo, Michael Hardy, MickMacNee, Mimigu, Moe Aboulkheir, Monfornot, Mpoloton, Munchtipq,
Myidbe, Oleg Alexandrov, Padrem, Pearle, Poodlelove, Prari, Quuxplusone, RadiantRay, Rashback, Reguiieee, Rethunk, RexNL, Rich Farmbrough, Rich8rd, Rlest, RomanZeyde, Ronaldo, Ronz,
Rror, Rwellington, Ryguasu, Salix alba, Salvio giuliano, Seabhcan, Shervinafshar, Shipmaster, SiobhanHansa, Sobasri, Solphusion, Stephen Rows, Stevekimcomcastnet, Taejo, Teacurran,
Tedickey, The undertow, The-thing, The1physicist, Timchanzee, Tommstein, Tpl, Tribaal, Tuxide, User A1, Vasileios Zografos, Visionwang, Wedesoft, Wereon, Wernher, Werratal, Wildknot,
Wimmerm, Wumpus3000, Yerpo, ‫ 982 ,ملاع بوبحم‬anonymous edits

Optical sorting Source: http://en.wikipedia.org/w/index.php?oldid=361734421 Contributors: Discospinster, Flightsoffancy, Paalappoo

Augmented Reality Source: http://en.wikipedia.org/w/index.php?oldid=174609072 Contributors: 22samurai, 2nova, Aaron.stafford, Abmac, Aeternus, Ahpook, Alinoz, Amorrow, Andy
Dingley, Anonymous Reviewer, Arch2all, Arsalank2, Ash, AugmentedReality, Averell23, Ayclove, Azwaldo, Back ache, BackwardsBoy, BaloneySausage, Bdwassom, Beeblebrox, Beebomb,
Benjsc, Bjeedit, Bkhn84, Blairmacintyre, Blumunky, BobKawanaka, Brett.lindberg, Btily, Byronknoll, Calvarer, Capricorn42, CaribDigita, CatherineMunro, CharlesC, ChickenChopps,
Chowbok, Chr15m, ChrisAR, Chrismanzione, Ckatz, Colinb, CommonsDelinker, Compvis, Coyoty, Cst17, Cybercobra, Cyclonenim, DXBari, Damane, Dandiggins, Danlev, Davepape, Ddxc,
Demosthenes2k8, Diceman, Discospinster, DocWatson42, Dogends, Dputig07, Dragice, Drgoldie, Duffhendrickson, Edward, Energy Dome, Eptin, Filthy swine, Firsfron, Frap, Frehley, Fthiess,
Furrykef, Fuzzy, Garyphayes, GeneralCheese, GianluigiCuccureddu, Gking92, Glogger, Gnomatic, Goplat, Gracefool, GraemeL, GregorB, GreySmallHorse, Gruszkad, Haakon, Hateless, Hcobb,
Hebrides, Honzibarak, Hthth, JQF, Jaceek, Janboonen, Jaranda, Jeffmcneill, Jgazelle, Jim.henderson, Jmartinezot, JohnOwens, Jonkerz, Jonpro, Josedavidcuartas, JumpMan2010, Just Another
Dan, Jutta, KBi, KLDavis, KYN, Karol Langner, Kcpenner, Kgrr, Konterfei, Kovos, KungFuMonkey, Kylin.Ma, Leafyplant, Leszek Jańczuk, LilHelpa, Madhugr, Malcolmxl5, Marcok,
Markdaams, Martarius, Massimo fontana, Mattgroves, Mattwilson0501, Merosonox, Mesler1537, Metaiouser, MichaelMcGuffin, Michal Nebyla, Milkinbags, MindWraith, Mohobo,
MorkaisChosen, Mr3641, Murmur001, N2e, Narkan, Natkeeran, Nbarth, Neurotropic, NovelIntellect, Obsessiveatbest, Opus 0, Paddles, PanagosTheOther, Patrick, Pbre71, PeterQuain,
PeterSF49, PhilKnight, Piano non troppo, Pieter-Paul, Pietjepuk67, Poko-chibi, Porslap, Prjacoby, Project2501a, Qluah, Quicorubio, RTC, Radagast83, Ralphybaby, Remshad, Riverside blue,
Rjwilmsi, RossTraversSmith, Russell Freeman, RyanTDMC, Sabretooth, Sagaciousuk, Sameboat, Schalliol, Schepop, Scmoatti, SeanMack, Serg3d2, Shanes, Shawnc, Shoehorn, Solphusion,
SoyYo, Spiffyxd, Steelbound, Strangebuttrue, SupperTina, Suryadas, Te2rx, Technobadger, Thbb, The Fish, TheDarkKnight42, Thelastminute, Thiseye, Tinmith, Tom harrison, TomPreuss,
TonyW, Toussaint, Unyoyega, VernoWhitney, Victoriagirl, Violetriga, Vizbi, Wapcaplet, Wavelength, Wik, Wikimonitorwest, Willifu, Xaosflux, Yarrik, Yashgaroth, Ynhockey, Ysangkok,
ZomBGolth, Zundark, ‫ 445 ,ناملس ىهن‬anonymous edits

Face detection Source: http://en.wikipedia.org/w/index.php?oldid=362704152 Contributors: Alcbwiki, Alexkonoplev, Alynna Kasmira, AnAj, Aranel, Calltech, Christopherlin, Cjsheets,
Dancter, Deisain, Devantheryv, Dicklyon, Dranaxum, Dreadstar, Dysprosia, Elkman, Epbr123, Feydey, Hanzzoid, Hike395, HooHooHoo, Indon, JForget, Kavitachate12, Lindsay658, MrOllie,
Neilc, NeuronExMachina, Nhbergboer, Nonpareility, Omidsakhi, Orderud, Powerslide, Random graffer, Random1973, Seabhcan, Sharakubj, Smileforwidjaja, Solphusion, Stephenb, Stonor, Tide
rolls, UberScienceNerd, Wavelength, WebHamster, Wooaf, Xanzzibar, 58 anonymous edits

Feature detection (computer vision) Source: http://en.wikipedia.org/w/index.php?oldid=343096224 Contributors: Anoko moonlight, AnthonyQBachler, David Eppstein, Hyperdeath,
Iknowyourider, Jasongallant, KYN, Kgwu24, KristinMiller, MrOllie, Mskayali, Mullderff, Philopp, Rbraunwa, Rbteye, Rjwilmsi, Tnxman307, Tpl, Utcursch, 6 anonymous edits

Lane departure warning system Source: http://en.wikipedia.org/w/index.php?oldid=357807959 Contributors: Alerante, Anthony Ivanoff, Anticipation of a New Lover's Arrival, The, Balou,
Bruce A. McHenry, CarSafety, Cvandanelzen, DeFacto, Dr. zedy, EmanWilm, Gaius Cornelius, GixxerSteve, GregorB, Hathawayc, HiNoony, Hooperbloob, HungryForNoodles, Innardskynard,
Janm67, KelleyCook, M-le-mot-dit, MTan355, Mac, Mailer diablo, Msiddi13, Myrtone86, NeilGoneWiki, Pineapple fez, Plasticup, Power1Pete, Ral315, Rjwilmsi, Rotarucalin, Sfoskett, Shane
Lawrence, Sladen, Slaweks, SynergyStar, TCY, TastyPoutine, Tevildo, The Founders Intent, UrmasU, Viewnyx, Viriditas, 91 anonymous edits

Non- photorealistic rendering Source: http://en.wikipedia.org/w/index.php?oldid=362869923 Contributors: Aaronh, Addshore, Adnanmg, Bcarrol, CLW, Chaleur, Cmsdengl, Danman60006,
Dhatfield, Edcolins, Gerbrant, Gilliam, GillianSmith, Hwang.roman, Isnow, Jcollomosse, Jhhays, Kelson Vibber, Khalfani khaldun, Killingthedream, Kmccoy, Mets501, Millionairex,
Movingimage, Panecasareccio, Pixaranimator, Richie, Simon the Dragon, Taw, Thelb4, Turtleheart, Vendettax, Welsh Cake Lover, 34 anonymous edits

Medical image processing Source: http://en.wikipedia.org/w/index.php?oldid=16590968 Contributors: 01bambern77, A314268, AED, AXu.VSI, Action potential, Adw2000, Alex.tan,
Altenmann, Altzinn, AndreasJS, Andrel, Anupam, Appraiser, Arcadian, Auntminnie, Aushulz, Austegard, Bazzargh, Beetstra, Beevee, Beland, Benjaminevans82, Berland, Beth.farrell, Bignoter,
Binksternet, Blowdart, Bme591wikiproject, Bradhegg, Btunell, CMD Beaker, Cameron.walsh, Can't sleep, clown will eat me, Canis Lupus, Cozmog, Cuthbertwong, DHN, DMacks, Darklilac,
David.Monniaux, Dicklyon, Dina, Discospinster, DocWatson42, Doczilla, Download, Dozen, Dr Zak, Draligus, Elsys, Erikp, Esprit15d, Ferengi, Flowerheaven, Freedomworks, Fumitol,
Fuzzball!, G3pro, Ganesha Freya, GargoyleMT, Gene Nygaard, Giftlite, Glitzy queen00, Goldencuboid, GordyB, Gradient11, GreatWhiteNortherner, GregorB, Gwernol, Hamanibrave,
Harrydevoil, HenryLi, Hoof Hearted, Hu12, IXICOexpert, Ian Pitchford, Ihealthbuzz, Imroy, Iweber2003, J04n, JVinocur, JaGa, Jamelan, JamesAM, Jengod, Jfdwolff, JimVC3, Jmanzanares,
Jmsc312, John.d.van.horn, Joshnpowell, Karada, Karnesky, Katiem222, Kauczuk, Khalid hassani, Khanafer, Kl4m-AWB, Klar sagen, Kram9, Ksiddiqui, Kubanczyk, LilHelpa, Loode,
Louislemieux, LuisIbanez, Lynnflint, MGlosenger, MMA Texas, Madmedea, Majeka, Mako098765, Mandy0147, Manwichosu, Marcika, Maximus Rex, Maxxicum, Mco44, Mdd, Mechanistic,
Med imaging, Melchoir, Mendaliv, Michael Snow, Miguel Andrade, Mikael Häggström, Mirada Medical, Morenus, MrOllie, Nachiketgokhale, NerdyNSK, Nevit, Oclatz, Ohnoitsjamie, Oli Filth,
Oxymoron83, Paranoid, Pde, Peterclipston, Peterkmoch, Petersam, Philipcosson, Philippe Nicolai-Dashwood, Pion, Publicoption, Pvosta, Radrounds, Rafaela.lamy, RedWolf, Rhcastilhos, Rich
Farmbrough, Rick Sidwell, Rjwilmsi, Robofish, Rphilipp, Rsabbatini, S0uj1r0, SYSS Mouse, Sabry hassouna, Sarahb87, Scottandrewhutchins, Seabhcan, ShakingSpirit, Shunpiker, Sietse Snel,
Simeon antonov, SimonaN, Sistromc, Sjschen, Slicky, Smocking, Snoogans1984, Solok7, Soundray, Spencer, Splmko, Stuartghall, Supten, Talented Mr Miller, The Anome, The Rationalist,
TheRealNightRider, Thekohser, Themfromspace, Thor Waldsen, Tpl, User A1, UzEE, Van helsing, Wavelength, Way4thesub, Weregerbil, Wilhelm Bauer, Xanzzibar, Xiggelee, Yoderj, Zereshk,
215 anonymous edits

Microscope image processing Source: http://en.wikipedia.org/w/index.php?oldid=340549748 Contributors: 1ForTheMoney, Altenmann, Anniebiogirl, Bryan Derksen, Cmdrjameson,
DavidWBrooks, GRAHAMUK, Hosse, JTN, Jackol, Karnesky, LeaveSleaves, Mahogny, Mdd, Orderud, Pvosta, Rubik-wuerfel, Schmiteye, Seabhcan, Skarebo, Snow Shoes, Tdi1, The Anome,
Tristanb, Watts52, Way4thesub, 31 anonymous edits

Morphological image processing Source: http://en.wikipedia.org/w/index.php?oldid=209179509 Contributors: 16@r, AxelBoldt, Charles Matthews, D6, Dai mingjie, Damian Yerrick, DePiep,
Erik Garrison, Folajimi, HenningThielemann, Isnow, JaGa, Jorge Stolfi, Kingpin13, Lamoidfl, LeaveSleaves, Linas, LindsayH, Martious, Mbell, Pakaraki, R'n'B, Radagast83, Renatokeshet, Salix
alba, Skittleys, Steadysteveo, SteveRwanda, The Firewall, Wprlh, 50 anonymous edits

Remote sensing Source: http://en.wikipedia.org/w/index.php?oldid=363191326 Contributors: Aarchiba, AgCam, Agge1000, Alansohn, AlexD, Amatulic, Anlace, Atmoz, Bart133, Beetstra,
Betterusername, Borgx, Bumbulski, CALR, CJLL Wright, Cantus, CarolSpears, Cartographic, Chris the speller, Ciphers, Ctroy36, Dhaluza, Dicklyon, Docoga, Dreadstar, Elchin, Elmore307,
EurekaLott, Eve Hall, Evercat, Ewlyahoocom, Excirial, Eyeintheskye, Fabartus, Fatnerf, Favonian, Fgnievinski, Fremsley, Frendinius, Fvw, GJo, Geologyguy, Gerrit, Gilliam, Gjd001, Gurch,
Hankwang, Hendee, HexaChord, Hildenja, Hooperbloob, Hugh16, Hvannorman, Hydrogen Iodide, Ian Pitchford, Igniateff, Iridescent, Isnow, Iszdfb, Itriel, JFBolton, JForget, JIP,
JamesBWatson, Jeff G., Jmnbatista, Joe fob, Jollyball, Jprikkel, JuanFox, Jusdafax, KYN, Kaisershatner, KeithTyler, Kir360, Knaartjie, KrOstir, KrakatoaKatie, Krash, Ktrudahl, LOL,
Lexcomber, Life of Riley, Lordsatri, Loren36, Lvhengani, MQ, Mac Davis, Mailseth, Maloelap, Maniraptor, Marcika, MartinHvidberg, MattDC, Maunaloaobservatory, Maurreen,
MelicansMatkin, Modulatum, MrBell, Mrs Trellis, N1RK4UDSK714, Natl1, Netalarm, Nihiltres, Noclevername, Ograps, Ohnoitsjamie, Oknedar, Oldtimer1820, Orlady, Orphan Wiki, Oxy10,
Oxymoron83, PFHLai, Pbeaty, Pflatau, Phi1365, PhilipO, Pinethicket, Pjblount, Punctilius, Qyd, Radical man 7, Radmap, Rag gupta, Rajeevmass, Raul654, Redline, Reedy, Regancy42, Regibox,
Rjwilmsi, Rudolf Pohl, Rumping, Saaga, Saber girl08, Samsara, Sarahb87, Seabhcan, Shadowjams, Shane.pearlman, Shaul1, Shelldrake07, Shiftchange, Siim, Sintaku, SkyWalker, Snowdog,
Someone42, SpaceFlight89, Stanton Hollister, StenSmith, Streltzer, StuffOfInterest, Subjectmatterexpert, Syrthiss, TCrossland, Tad.k.22, Tarantola, TestPilot, The Random Editor, Tm3108,
Todddouglastaylor, Vsmith, Walor, Webschem, Whosasking, William M. Connolley, 295 anonymous edits

Medical imaging Source: http://en.wikipedia.org/w/index.php?oldid=360755398 Contributors: 01bambern77, A314268, AED, AXu.VSI, Action potential, Adw2000, Alex.tan, Altenmann,
Altzinn, AndreasJS, Andrel, Anupam, Appraiser, Arcadian, Auntminnie, Aushulz, Austegard, Bazzargh, Beetstra, Beevee, Beland, Benjaminevans82, Berland, Beth.farrell, Bignoter, Binksternet,
Blowdart, Bme591wikiproject, Bradhegg, Btunell, CMD Beaker, Cameron.walsh, Can't sleep, clown will eat me, Canis Lupus, Cozmog, Cuthbertwong, DHN, DMacks, Darklilac,
David.Monniaux, Dicklyon, Dina, Discospinster, DocWatson42, Doczilla, Download, Dozen, Dr Zak, Draligus, Elsys, Erikp, Esprit15d, Ferengi, Flowerheaven, Freedomworks, Fumitol,
Fuzzball!, G3pro, Ganesha Freya, GargoyleMT, Gene Nygaard, Giftlite, Glitzy queen00, Goldencuboid, GordyB, Gradient11, GreatWhiteNortherner, GregorB, Gwernol, Hamanibrave,
Harrydevoil, HenryLi, Hoof Hearted, Hu12, IXICOexpert, Ian Pitchford, Ihealthbuzz, Imroy, Iweber2003, J04n, JVinocur, JaGa, Jamelan, JamesAM, Jengod, Jfdwolff, JimVC3, Jmanzanares,
Jmsc312, John.d.van.horn, Joshnpowell, Karada, Karnesky, Katiem222, Kauczuk, Khalid hassani, Khanafer, Kl4m-AWB, Klar sagen, Kram9, Ksiddiqui, Kubanczyk, LilHelpa, Loode,
Louislemieux, LuisIbanez, Lynnflint, MGlosenger, MMA Texas, Madmedea, Majeka, Mako098765, Mandy0147, Manwichosu, Marcika, Maximus Rex, Maxxicum, Mco44, Mdd, Mechanistic,
Med imaging, Melchoir, Mendaliv, Michael Snow, Miguel Andrade, Mikael Häggström, Mirada Medical, Morenus, MrOllie, Nachiketgokhale, NerdyNSK, Nevit, Oclatz, Ohnoitsjamie, Oli Filth,
Oxymoron83, Paranoid, Pde, Peterclipston, Peterkmoch, Petersam, Philipcosson, Philippe Nicolai-Dashwood, Pion, Publicoption, Pvosta, Radrounds, Rafaela.lamy, RedWolf, Rhcastilhos, Rich
Farmbrough, Rick Sidwell, Rjwilmsi, Robofish, Rphilipp, Rsabbatini, S0uj1r0, SYSS Mouse, Sabry hassouna, Sarahb87, Scottandrewhutchins, Seabhcan, ShakingSpirit, Shunpiker, Sietse Snel,
Simeon antonov, SimonaN, Sistromc, Sjschen, Slicky, Smocking, Snoogans1984, Solok7, Soundray, Spencer, Splmko, Stuartghall, Supten, Talented Mr Miller, The Anome, The Rationalist,
TheRealNightRider, Thekohser, Themfromspace, Thor Waldsen, Tpl, User A1, UzEE, Van helsing, Wavelength, Way4thesub, Weregerbil, Wilhelm Bauer, Xanzzibar, Xiggelee, Yoderj, Zereshk,
215 anonymous edits

Image Sources, Licenses and Contributors 83

Image Sources, Licenses and Contributors
Image:Image in Glossographia.png Source: http://en.wikipedia.org/w/index.php?title=File:Image_in_Glossographia.png License: Public Domain Contributors: Alphachimp, DanielPharos,
Dicklyon, 2 anonymous edits
Image:Raster to Vector Mechanical Example.jpg Source: http://en.wikipedia.org/w/index.php?title=File:Raster_to_Vector_Mechanical_Example.jpg License: Public Domain Contributors:
Ilmari Karonen, Ma-Lik, The Evil IP address, Yyy, 4 anonymous edits
Image:Pixel-example.png Source: http://en.wikipedia.org/w/index.php?title=File:Pixel-example.png License: Creative Commons Attribution-Sharealike 2.5 Contributors: User:ed_g2s
Image:Closeup of pixels.JPG Source: http://en.wikipedia.org/w/index.php?title=File:Closeup_of_pixels.JPG License: GNU Free Documentation License Contributors: User:Kprateek88
Image:ReconstructionsFromPixels.png Source: http://en.wikipedia.org/w/index.php?title=File:ReconstructionsFromPixels.png License: Public Domain Contributors: Original uploader was
Dicklyon at en.wikipedia
Image:Wikipedia ClearType.png Source: http://en.wikipedia.org/w/index.php?title=File:Wikipedia_ClearType.png License: Public Domain Contributors: Jesse Viviano, Pabouk, Qz,
Remember the dot
Image:Pixel geometry 01 Pengo.jpg Source: http://en.wikipedia.org/w/index.php?title=File:Pixel_geometry_01_Pengo.jpg License: unknown Contributors: User:Pengo
Image:Vector Video Standards2.svg Source: http://en.wikipedia.org/w/index.php?title=File:Vector_Video_Standards2.svg License: GNU Free Documentation License Contributors:
User:Hdante
Image:Imagen binaria.jpg Source: http://en.wikipedia.org/w/index.php?title=File:Imagen_binaria.jpg License: Public Domain Contributors: Cyborg, Ma-Lik, 2 anonymous edits
Image:Alleia Hamerops composite.jpg Source: http://en.wikipedia.org/w/index.php?title=File:Alleia_Hamerops_composite.jpg License: unknown Contributors: Berillium, GoClick, Gorgo,
Ma-Lik, Mdd4696
Image:NASA Mars Rover.jpg Source: http://en.wikipedia.org/w/index.php?title=File:NASA_Mars_Rover.jpg License: Public Domain Contributors: Image by Maas Digital LLC for Cornell
University and NASA/JPL
Image:Augmented_GeoTravel.jpg Source: http://en.wikipedia.org/w/index.php?title=File:Augmented_GeoTravel.jpg License: Public Domain Contributors: GreySmallHorse
Image:Wikitude.jpg Source: http://en.wikipedia.org/w/index.php?title=File:Wikitude.jpg License: Creative Commons Attribution-Sharealike 3.0 Contributors: User:Mr3641
Image:Image-AR TD0.jpg Source: http://en.wikipedia.org/w/index.php?title=File:Image-AR_TD0.jpg License: Public Domain Contributors: MichaelMaggs, Serg3d2, Tryphon, Was a bee
Image:Milgram Continuum.png Source: http://en.wikipedia.org/w/index.php?title=File:Milgram_Continuum.png License: Creative Commons Public Domain Contributors: User:Drgoldie
Image:Mediated reality continuum 2d.png Source: http://en.wikipedia.org/w/index.php?title=File:Mediated_reality_continuum_2d.png License: Creative Commons Attribution-Sharealike 3.0
Contributors: User:Glogger
Image:commons-logo.svg Source: http://en.wikipedia.org/w/index.php?title=File:Commons-logo.svg License: unknown Contributors: Geekybroad, Harryboyles, Jezerfetnae, Kbdank71,
MSGJ, Mike5904, RockMFR, Stephen Bain, Who, 17 anonymous edits
Image:Corner.png Source: http://en.wikipedia.org/w/index.php?title=File:Corner.png License: Public Domain Contributors: McLoaf, Retardo
File:Strada Provinciale BS 510 Sebina Orientale.jpg Source: http://en.wikipedia.org/w/index.php?title=File:Strada_Provinciale_BS_510_Sebina_Orientale.jpg License: GNU Free
Documentation License Contributors: User:Grasso83
Image:Brain Mri nevit.svg Source: http://en.wikipedia.org/w/index.php?title=File:Brain_Mri_nevit.svg License: GNU Free Documentation License Contributors: Nevit Dilmen
Image:DilationErosion.png Source: http://en.wikipedia.org/w/index.php?title=File:DilationErosion.png License: Public Domain Contributors: Renato Keshet
Image:Erosion.png Source: http://en.wikipedia.org/w/index.php?title=File:Erosion.png License: GNU Free Documentation License Contributors: Lights, Renatokeshet
Image:Dilation.png Source: http://en.wikipedia.org/w/index.php?title=File:Dilation.png License: Public Domain Contributors: Renatokeshet
Image:Opening.png Source: http://en.wikipedia.org/w/index.php?title=File:Opening.png License: Public Domain Contributors: Renatokeshet
Image:Closing.png Source: http://en.wikipedia.org/w/index.php?title=File:Closing.png License: Public Domain Contributors: Renatokeshet
Image:Death-valley-sar.jpg Source: http://en.wikipedia.org/w/index.php?title=File:Death-valley-sar.jpg License: Public Domain Contributors: NASA/JPL
Image:Usaf.u2.750pix.jpg Source: http://en.wikipedia.org/w/index.php?title=File:Usaf.u2.750pix.jpg License: unknown Contributors: Ktr101, Nyenyec
Image:2001 mars odyssey wizja.jpg Source: http://en.wikipedia.org/w/index.php?title=File:2001_mars_odyssey_wizja.jpg License: Public Domain Contributors: NASA

License 84

License
Creative Commons Attribution-Share Alike 3.0 Unported
http:/ / creativecommons. org/ licenses/ by-sa/ 3. 0/

Image Processing

More Related Content

What's hot (20)

Similar to Image Processing (20)

Recently uploaded (20)

Image Processing