Comparative Study of Convolution Based Inpainting Algorithms

IJSRD - International Journal for Scientific Research & Development| Vol. 2, Issue 08, 2014 | ISSN (online): 2321-0613
All rights reserved by www.ijsrd.com 201
A Smart Approach to Number Plate Recognition in Tollgate System
Using FPGA
S. Lokesh1
N. Ashok Kumar2
1
M. Tech Final Year Student 2
Associate Professor
1
Avanthi’s Scientific Technological & Research Academy, Telangana
Abstract— This paper reveals about the design and
development of smart card for automated toll collection
through number plate recognition. Since it is simpler and
faster than the traditional token based ticket system, it has
all the potential to replace the existing system. Moreover, it
saves users valuable time by reducing the queue length in
front of the toll counter. It is used to pay the amount
automatically and open & close the toll gate automatically.
We aim to reduce the time consumed to pay the toll gate
amount and also to help the police department to trace the
vehicle, incase if it was stolen or used for any illegal
activities. As well as we are going to increase the security
features in the toll gate because now a day’s toll gate are the
entrance to the main cities. If the Vehicle passed before
paying the money the buzzer will automatically ring & the
alert will be given to the police also. If any vehicle carries
suspicious gas means the buzzer will ring so improved
security than the existing systems. The entire system is
developed as hardware based system using SPARTAN3
FPGA kit and associated devices. The software for this
system has been developed using VHDL language
developed in the Xilinx tool.
Key words: Dilation, Segmentation, Erosion, ANPR, RFID
I. INTRODUCTION
Toll gates are usually considered an inconvenience by
travellers not only for the cost of the toll, but also for the
delays at toll booths, toll roads and bridges. In order to
ensure a steady flow of traffic, both staff and drivers require
easy access to an efficient communication system covering
the specific requirements of toll gates. In this way, hitches
can be resolved while maintaining a convenient toll gate
system. Security systems can also be added, which will
further enhance the system.
The toll gate system using ANPR technology
enables the electronic collection of toll payments. This
technology has been studied by researchers and applied in
various highways, bridges, and tunnels requiring such a
process. This system is capable of determining if the car is
registered or not, and then informing the authorities of toll
payment violations, debits etc. The most obvious advantage
of this technology is the opportunity to eliminate congestion
in tollbooths, especially during festive seasons when traffic
tends to be heavier than normal. It is also a method by which
to curb complaints from motorists regarding the
inconveniences involved in manually making payments at
the tollbooths. Other than this obvious advantage is that it
could also benefit the toll operators.
II. IMPLEMENTATION
A. Existing System
The existing system consists of a microcontroller, RFID
reader, RFID Tag, stepper motor, and bill printer. The reader
retrieves the information about the ID number and identifies
the vehicle. Then for the tax to be collected the bill is
printed at the time of exit. The stepper motor here is used to
open and close the gate automatically.
In the existing system, though there is an RFID
reader the tax collection is manual and not automated. There
are no security features such as identifying a stolen vehicle
etc. The toll tax which is collected for all the vehicles is the
same and the tax collected is not based on the load carried
by the vehicle.
1) Drawbacks of Existing System:
 Sensitive to noise and it may generate error during
detection
 Computationally complex and Time consuming
B. Proposed Technique
The proposed system makes sure that the traffic at the toll
gates is streamlined and security is also present. The tax
which is collected is based on the load carried by the
vehicle. Through this system we can also identify stolen
vehicles.
Toll on each vehicle will be charged proportional
to its weight/load & at the same time vehicle will be scanned
for unlawful material. For justifying our concept we are
using a gas sensor.
Weight will be calculated using a load cell. Load
cell & proximity sensor output will be given to an ADC0809
which digitized signals.
Weight & its corresponding toll & the amount paid
by vehicle owner will be calculated using a FPGA.
Programming language used is VHDL for hardware of these
operations.
Weight of the vehicle & its toll both
simultaneously will be displayed on the PC screen.
The vehicle owner/driver pays toll according to
displayed amount on the monitoring screen will be reduced
from their online account.
If in case owner/driver tried to escape with
unwanted material & try to break the gate 1 a siren will buzz
at the nearest security center & emergency heavy gate 2 will
be pulled down automatically using RF module & vehicle
will be blocked.
In such case a strict action will be taken over
blocked vehicle.
Being the toll is charged depending on the weight
sensed, no customer have the loss of even carrying a vacant
vehicle.
Due to the use of RF receiver & transmitter
wireless communication has become possible due to which
the next door can be closed in order to avoid the cheating.
The proximity sensor used here detects if any
unauthorized material is being passed via the vehicle.
RF transmitter & receiver used have limited range
up to 30 meters in our project. This range will also be
increased in future developments as the range of transmitter
& receiver will be increased.

A Smart Approach to Number Plate Recognition in Tollgate System Using FPGA
(IJSRD/Vol. 2/Issue 08/2014/048)
III. WORKING PRINCIPLE
AUTOMATIC license plate recognition (LPR) plays an
important role in numerous applications such as unattended
parking lots security control of restricted areas traffic law
enforcement congestion pricing and automatic toll
collection. Due to different working environments, LPR
techniques vary from application to application. Pointable
cameras create dynamic scenes when they move, pan or
zoom. A dynamic scene image may contain multiple license
plates or no license plate at all. Moreover, when they do
appear in an image, license plates may have arbitrary sizes,
orientations and positions. And, if complex backgrounds are
involved, detecting license plates can become quite a
challenge. Typically, an LPR process consists of two main
stages (1) locating license plates and (2) identifying license
numbers. In the first stage, license plate candidates are
determined based on the features of license plates. Features
commonly employed have been derived from the license
plate format and the alphanumeric characters constituting
license numbers. The features regarding License plate
format include shape, symmetry height-to width ratio color
texture of grayness spatial frequency and variance of
intensity values Character features include line blob the sign
transition of gradient magnitudes, the aspect ratio of
characters the distribution of intervals between characters
and The alignment of characters. In reality, a small set of
robust, reliable, and easy-to-detect object features would be
adequate.
The license plate candidates determined in the
locating stage are examined in the license number
identification stage. There are two major tasks involved in
the identification stage, Number separation and Number
recognition. Number separation has in the past been
accomplished by such techniques as projection morphology
relaxation labeling, connected components and blob
coloring. Since the projection method assumes the
orientation of a license plate is known and the morphology
method requires knowing the sizes of characters. A hybrid
of connected components and blob coloring techniques is
considered for character separation. Support Vector machine
Markov processes and finite automata these methods can be
broadly classified into iterative and Non-iterative
approaches. There is a tradeoff between these two Groups of
approaches; iterative methods achieve better accuracy, but at
the cost of increased time complexity. For this, we
developed our own character recognition technique, which
is based on the disciplines of both artificial neural networks
and mechanics.
IV. IMPLEMENTATION
Figure 1 shows the proposed system. The ANPR systems
compare the input number plate image with the database. PC
consists of the entire database which is updated periodically.
Now after reading the information, PC compares the data in
the database and allows the access accordingly by
opening/closing the gate. This data is used to print a daily or
monthly bill for toll collection from the vehicles. This way
even stolen vehicle can be also identified.
The pressure of the vehicle is obtained using the
pressure sensor and accordingly the pressure of the vehicle
is displayed on the display. A counter is used to count the
number of vehicles. The amount on the basis of weight &
the count of vehicles is also displayed on the screen. The
amount to be paid is automatically deduced from the
respective bank account.
Fig. 1: Block Diagram of proposed system
If a vehicle carries any kind of gas that shouldn’t
be carried, the gas sensor detects the gas in the vehicle. In
case if there is any kind of gas that is detected, the RF
transmitter is used to alert the nearby police station and an
alarm is enabled to alert the surrounding areas. Subsequently
motor 1 is used to close the gate and simultaneously motor 2
is used to pull up the spikes in order to puncture the vehicle.
The flowchart for the entire process is shown in figure 3.2
Fig. 2: Flowchart for the proposed system

Fig. 3: Proposed ANPR System
V. TECHNICAL DETAILS
A. Segmentation – License Plate detection
The goal of image segmentation is to cluster pixels into
salient image regions, i.e., regions corresponding to
individual surfaces, objects, or natural parts of objects. In
computer vision segmentation refers to the process of
partitioning a digital image to multiple segments. The goal
of segmentation is to simplify and/or change the
representation of an image into something that is more
meaningful and easier to analyze Image segmentation is
typically used to locate objects and boundaries (lines,
curves, etc.) in images. More precisely, image segmentation
is the process of assigning a label to every pixel in an image
such that pixels with the same label share certain visual
characteristics.
The result of image segmentation is a set of
segments that collectively cover the entire image, or a set of
contours extracted from the image. Each of the pixels in a
region are similar with respect to some characteristic or
computed property, such as color, intensity, or texture,
Adjcent regions are significantly different with respect to
the same characteristics.
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.
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 theoretical foundation.
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)}.
B. 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.
1) Erosion
Fig. (3): Erosion illustration
The erosion of the dark-blue square by a disk,
resulting in the light-blue square.
The erosion of the binary image A by the
structuring element B is defined by:
Where Bz is the translation of B by the vector z,
i.e.,
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".
2) Dilation
Fig 4: Dilation illustration
The dilation of the dark-blue square by a disk,
resulting in the light-blue square with rounded corners.
The dilation of A by the structuring element B is
defined by:
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.
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.
3) Opening
The opening of the dark-blue square by a disk, resulting in
the light-blue square with round corners.
Fig. 5: Opening illustration

The opening of A by B is obtained by the erosion
of A by B, followed by dilation of the resulting image by B:
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.
4) Closing
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.
Fig. 6: Closing illustration
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 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.
5) Dilation and Erosion
From these two Minkowski operations we define the
fundamental mathematical morphology operations dilation
and erosion:
 Dilation:
 Erosion:
Where these two operations are illustrated in Figure
37 for the objects defined in Figure 35.
(A) Dilation D (A, B) (B) Erosion E (A, B)
Figure 7: A binary image containing two object
sets A and B. The three pixels in B are "color-coded" as is
their effect in the result.
While either set A or B can be thought of as an
"image", A is usually considered as the image and B is
called a structuring element. The structuring element is to
mathematical morphology what the convolution kernel is to
linear filter theory.
6) Summary of the basic operations
The results of the application of these basic operations on a
test image are illustrated below. In Figure 40 the various
structuring elements used in the processing are defined. The
value "-" indicates a "don't care". All three structuring
elements are symmetric.
Fig. 8: Structuring elements B, B1, and B2 that are 3 x 3 and
symmetric.
The results of processing are shown in Figure 9
where the binary value "1" is shown in black and the value
"0" in white.
Image A
Dilation with 2B
Erosion with 2B
Opening with 2B
Closing with 2B
H it-and-Miss with B1 and B2
Fig. 8: Examples of various mathematical morphology
operations.
The opening operation can separate objects that are
connected in a binary image. The closing operation can fill
in small holes. Both operations generate a certain amount of
smoothing on an object contour given a "smooth"
structuring element. The opening smoothes from the inside
of the object contour and the closing smoothes from the

outside of the object contour. The hit-and-miss example has
found the 4-connected contour pixels.
VI. RESULTS
The results obtained using our proposed system is as follows
Fig. 9: Overall Hardware
In the above figure consist of a FPGA, RF
transmitter, RF receiver, RFID Reader, gas sensor, pressure
sensor, motors and relay which are connected together. Our
project is a unmanned toll gate system which makes toll tax
to be collected automatically, provides security, and traffic
free which does not require any manual supervision. If any
vehicle is stolen are gas is carried then it immediately
alarms the surroundings and to the nearby police station in
the mean while it switches on the motor 1 and 2. Here motor
1 is a shaft and motor 2 produces spikes.
Fig. 10: Basic View
Fig. 11: After Adding The Database
Fig. 12: Segmentation
Fig. 13: After Recognition
Fig. 14: Amount and pressure chart
VII. CONCLUSION
Our system is a user friendly toll fee method which can save
time and reduce traffic congestion at toll gates and provide
solution for users to reach their destination without wastage
of time. It gives the toll authorities the flexibility to set
variable pricing for toll services and thus a fair policy of tax
collection can be followed. This way there is no loss
incurred by a person carrying a vacant vehicle. With the
hike of fuel prices in mind, consumption of fuel is also
considered here as the deceleration, acceleration and idling
is completely eliminated. Here there is no cash transaction
for the toll lanes, so cash handling is reduced. Thus
difficulties with cash handling are eliminated and this way
aid in enhanced audit control by centralizing user accounts.
Information such as vehicle count over the time of the day,
date, time etc can be obtained due to the deployment of this
technology. This helps in making decisions regarding the
pricing strategies for the toll providers. It also helps planner
to estimate the travel time that aid in designing decisions.
FUTURE ENHANCEMENT
In future the speed of the process can be increased further.
Similarly we can add an additional feature such as adding a
metal detector in order to detect the arms that are carried.

REFERENCES
[1] Gautier, Philippe; Gonzalez, Laurent (2011).
L'Internet des Objets.Internet, mais en mieux.
foreword by Gérald Santucci (European
commission), postword by Daniel Kaplan (FING)
and Michel Volle. Paris: AFNOR editions.ISBN
978-2-12-465316-4.
[2] Ericson White Paper, “More Than 50 Billion
Connected Devices” 284 23-3149 Uen, February
2011.
[3] Guinard D, Trifa V, Wilde E (2010c) A Resource
Oriented Architecture for the Web of Things.
Proceedings of IoT 2010, IEEE International
Conference on the Internet of Things. Tokyo, Japan
[4] D. Guinard, V. Trifa, F. Mattern, and E. Wilde.
From the Internet of Things to the Web of Things:
Resource Oriented Architecture and Best Practices.
In D. Uckelmann, M. Harrison, and F. Michahelles,
editors, Architecting the Internet of Things, chapter
5. Springer.
[5] M.Wang, C.Fan, Z.Wen, S.Li, J.Liu, "
Implementation of Internet of Things Oriented Data
Sharing Platform Based on RESTful Web Service”,
7th International Conference on Wireless
Communications, Networking and Mobile
Computing (WiCOM), 2011
[6] W. Colitti, K. Steenhaut, and N. De Caro,
“Integrating Wireless Sensor Networks with the
Web,” in Extending the Internet to Low powerand
Lossy Networks (IP+SN 2011), 2011.
[7] Ari Juels, RFID Privacy:A Technical Primer For
The Non-Technical Reader, Draft: 23 February
2005, RSA Laboratories, Bedford, MA, USA
[8] Baronti et al., 2007, ” Wireless sensor networks: A
survey on the state of the art and the 802.15.4 and
ZigBee standards”, Computer Communications 30
(2007) 1655–1695.
[9] L. Ruiz-Garcia , P. Barreiro , J.I. Robla ,
”Performance of ZigBee-Based wireless sensor
nodes for real-time monitoring of fruit logistics”,
Centro Nacional de Investigaciones Metalurgicas
(CENIM-CSIC), Avda. Gregorio del Amo, 8, 28040,
Madrid, Spain
[10]Kushalnagar, N, IPv6 over Low-Power Wireless
Personal Area Networks (6LoWPANs): Overview,
Assumptions, Problem Statement, and Goals. RFC
4919.
[11]Shelby, Z., et al. Constrained Application Protocol
(CoAP) Internet- Draft. draft-ietf-core-coap-11.
[12]Shelby & Bormann, “The Wireless Embedded
Internet” ISBN: 978-0- 470-74799-5, (c) 2009 John
Wiley & Sons Ltd
[13]Hartke, K., et al. Observing Resources in CoAP.
Internet-Draft. draftietf- core-observe-06.
[14]Gamma, E., Helm, R., Johnson, R., and J.
Vlissides,"Design Patterns:
[15]Elements of Reusable Object-Oriented Software",
Addison-Wesley, Reading, MA, USA, November
1994.
[16]Daniele Catteddu and Giles Hogben, “Cloud
Computing : Benefits, Risks and Recommendations
for Information Security”, European Network and
Information Security Agency (ENISA), 2009

Comparative Study of Convolution Based Inpainting Algorithms

More Related Content

What's hot (20)

Viewers also liked (16)

Similar to Comparative Study of Convolution Based Inpainting Algorithms (20)

More from ijsrd.com (20)

Recently uploaded (20)

Comparative Study of Convolution Based Inpainting Algorithms