IRJET- Face Counter using Matlab

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 05 Issue: 04 | Apr-2018 www.irjet.net p-ISSN: 2395-0072
© 2018, IRJET | Impact Factor value: 6.171 | ISO 9001:2008 Certified Journal | Page 501
FACE COUNTER USING MATLAB
Prof. Kumthekar.A.V1, Shraddha Dale2, Dhanashri Chavan3, Jyoti Mali4
1Asst.Prof. Department of Electronics and telecommunication engineering, AGTI’S Dr. Daulatrao Aher College Of
Engineering, Karad. Maharashtra, India.
2&3&4 Student of Department of Electronics and telecommunication engineering, AGTI’S Dr. Daulatrao Aher College
Of Engineering, Karad. Maharashtra, India.
------------------------------------------------------------------------------***---------------------------------------------------------------------------
Abstract-This paper presents the automatic people face
counting in a classroom using MATLAB. Where the
number of people present at the specific location, this
system used to count people face present in desired
location with high accuracy using video camera, where
count the people faces in real time. The basic idea to first
use the frame difference to detect the rough edges of the
people face, morphological processing, skin color
detection, face feature detection and last count the human
faces.
Key words: Moving object segmentation, Skin color,
Webcam, GUI, Time
1.INTRODUCTION-
In day to day life the counting students in a classroom is
done manually ,it consumes large time, also distraction
of students such that this project to count the number of
students present according schedule of lectures. It gives
the accurate data of the number of students present in
the any lecture or practical. It doesn’t require anytime.
Attendance monitoring is important in school and
colleges the teacher are counting the total students
presents in class but sometime they make mistakes so
count is not accurate due to this error are caused in final
count. So this problem is solved using this face counter
system. This time is based on real time.Any large
industry number according to their number of days are
they work are counted automatically and the end of the
month we pay them salary easily.One of the important
applications of counting includes counting people easily
in a hall or in a shopping mall etc. People can be counted
based on the number of faces detected. Face detection is
the process in which the human faces are detected from
a color image. Once the number of faces are detected the
density can be calculated. There are many ways by which
faces can be detected one such method is skin based
detection. Rectangles can be used to map the faces in the
image. Face detection is used in many day today
application.The automatically face counting using the
system of face counter where the counting is highly
challenging where some variety of techniques or
Parameters are used to proposed by the face counting
system. Some techniques are moving object
segmentation, skin color detection, face detection and
counting. The skin color detection to improve the
accuracy of the face detection we applied the reference
white with NCC(Normalized Color Coordinates) color
spaced consider with balance white color automatically
and changes of skin color in images caused by intensity
difference in light.
MATLAB-
MATLAB is a high-representation language for technical
performance. It integrates computation, contemplate,
and programming in an easy-to-working area where
problems and solutions are state in familiar notations.
Standard utilize are following:
• Mathematics and estimate.
• Creating algorithms
• Data obtain.
• Modeling and prototyping
• Data analysis and contemplate
MATLAB is the computational utilize choice for research,
development, and obtain.It has image processing tools
which are used in processing.
• MATLAB is the level of contemplate environment for all
working fields.
• MATLAB has various other tools which are used in
mathematical, scientific, engineering etc. It also provides
a GUI interface.
2. Literature survey-
1.Mora Albiol and V. Naranjo, “Real time high density
people counter using morphological tools”(Dec 2001)-
This paper deals with an application of image sequence
analysis and number of people who get into and out of
train carriage when it is crowded, and background and
or illumination changes. The proposed system analyzes
image sequences and processes them using an algorithm
based on the use of several morphological tools which
are presented in detailed in the paper.
2,T.H. Chen, T.Y. Chen, “An intelligent people flow
counting method for passing through gate”(June 2006)-
This paper presents automatic people counting system
based on face detection, where the number of people
passing through a gate or a door.

3.Work flow of proposed system-
3.1 Work flow description-
3.1.1. Frame difference-In this moving object
segmentation is used. This method is proposed to the
deleting a general moving object background. The
background subtraction method is used this method
means subtracts the background it doesn’t include faces.
The background subtraction doesn’t accurate, so we use
this technique. In this filter is used by using filter to
remove noise in moving object segmentation.
3.1.2.Morphological processing- The morphological
concepts and technique are used in project is a powerful
set of tools for extracting feature of interest in an image
component and description of region shape such as
boundaries, skeleton and the convex hull. One of the
most appealing aspects of morphological image
processing is the extensive set theoretical foundation
from which morphological technique are evolved. In fig a
image are binary, with 1’s shown shaded and 0’s shown
white.
3.1.2.1.Morphological operations-
1. Erosion-This is an operation that thins or subtracts the
objects in the binary image. T
2. Dilution- This is an operation that grows or thickens
the objects in a binary image
3.1.3. Skin color detection- In this skin color detection
technique to improve accuracy of the face detection to
used normalized color coordinates (NCC) the image
processing toolbox handle all color images either as
method construct background model and remove the
foreground image by the using frame difference
operation between the captured image and image
sequence. Some of the system the background
subtraction indexed images or RGB (Red Blue Green).
Skin color detection is the process of separation between
skin and non-skin pixels. It is difficult to develop uniform
method for the segmentation or detection of human skin
detection because the color tone of human skin is
drastically varied for people one region to another.
3.1.4. Face feature detection-
Face feature detection which detects facial expression
which have applications face recognition, head pose
estimation and face morphing. This system based on face
detection using matlab that can detect not only a human
face but also, eyes and upper body. With the skin tone
selected as the feature to track
3.1.5. Face tracking and Display count- Total number
of faces present in current image that count will display
on screen. We set up a counting line in the image. If the
moving objects (human face) entry the tracking area, we

analyze the center of the face to get the tracked objects
moving direction. Then, we count the face passing
through the tracking area.
If the human faces move, the coordinates of the center
will change during the different time periods. However,
the moving volume of the center is limited between two
adjacent images. We measure the moving volume of the
center between two adjacent images though Euclidean
distance. The Euclidean distance formula is shown as the
following:
Dist = sqrt ((xt-xt-1)2+ (yt-yt-1)2)
Where the t is denoted as the time, (x, y) is
denoted as the coordinates of the center.
4. RESULT-
In the finally this project count the number of faces. Such
that this system used as attendance for industrial
applications. By using employees data base such as
persons name, address, mobile number by that
information verifies person. Where data base already
registered and finally at last number of faces detected.
This window shows the count of detected faces and
verifies and registration of the captured faces from the
camera as well as webcam.In this system, all these
elements modeled through a desktop metaphor to
produce a simulate in the software in which the display
represent the GUI window, on which documents and
folders of documents can be registered . Window
managers and other software combined to simulate the
desktop environment with varying degrees of realism.
5.CONCLUSION-
The computational models, which were implemented in
this project, were chosen after extensive research, and
the successful testing results confirm that the choices
made by the researcher were reliable .The system with
manual face detection and automatic face recognition did
not have a recognition accuracy over 90%, due to the
limited number of eigenfaces that were used for the PCA
transformed. This system was tested under very robust
conditions in this experimental study and it is envisaged
that real-world performance will be far more accurate.
The fully automated frontal view face detection system
displayed virtually perfect accuracy and in the
researcher's opinion further work need not be
conducted in this area. The fully automated face
detection and recognition system was not robust enough
to achieve a high recognition accuracy. The only reason
for this was the face recognition subsystem did not
display even a slight degree of invariance to scale,
rotation or shift errors of the segmented face image.
However, if some sort of further processing, such as an
eye detection technique, was implemented to further
normalize the segmented face image, performance will
increase to levels comparable to the manual face
detection and recognition system. Implementing an eye
detection technique would be a minor extension to the
implemented system and would not require a great deal
of additional research. All other implemented systems
displayed commendable results and reflect well on the
deformable template and Principal Component Analysis
strategies. The most suitable real-world applications for
face detection and recognition systems are for mug shot
matching and surveillance.
ACKNOWLEDGEMENT
Professor A. V. Kumthekar. our supervisor, philosopher
and personality with a Midas touch encouraged us to
carry this work. His continuous invaluable knowledgably
guidance throughout the project of this study helped us
to complete the work up to this stage and hope will
continue in further research.
REFERENCES-
[1].Mora Albiol and V. Naranjo, “Real time high density
people counter using morphological tools” (Dec.2001)-
[2]T.H.Chen, T.Y.Chen and Z.X.Chen,” An intelligent
people flow counting method for passing through
gate”(June 2006)-
[3]Rafael C. Gonzalez, Richard E. Woods “Book on Digital
Image Processing”

IRJET- Face Counter using Matlab

More Related Content

What's hot (20)

Similar to IRJET- Face Counter using Matlab (20)

More from IRJET Journal (20)

Recently uploaded (20)

IRJET- Face Counter using Matlab