Real time voting system using face recognition for different expressions and pose variations

IJRET: International Journal of Research in Engineering and Technology eISSN: 2319-1163 | pISSN: 2321-7308
_______________________________________________________________________________________
Volume: 03 Issue: 07 | Jul-2014, Available @ http://www.ijret.org 381
REAL TIME VOTING SYSTEM USING FACE RECOGNITION FOR
DIFFERENT EXPRESSIONS AND POSE VARIATIONS
Ganapatikrishna P. Hegde1
, M. Seetha2
1
Asst. Professor, Dept of Cpmputer & Engineering, SDM Insitute of Technology, Ujire
2
Professor, Dept. Computer Science & Engineering, GNITS, Hyderabad
Abstract
In this research work different facial expressions and poses of individual person faces are detected and stored in voter database
by giving appropriate aadhar card id number. If a person comes for a vote then his or her face is detected and this detected face
image is compared with images in voter database and aadhar card id number. If the face image and id number are recognized
then person is allowed to cast the vote. If it is not recognized then person is not allowed to vote. After the successful voting
process, number of votes to the particular candidate and the party will be counted. This paper illustrates the Haar like features
for face detection and eigenface algorithm for face recognition. eigenface method is one of the most basic and efficient methods
for face recognition. This paper also shows that if the minimum Euclidian distance from other images of the test image is zero,
then the test image absolutely matches the existing image in the database.
--------------------------------------------------------------------***------------------------------------------------------------------
1. INTRODUCTION
There are various significant applications of face feature
extraction and recognition are face based electronic voting
system, video indexing and browsing engines, biometric
identity authentication, multimedia management, human-
computer interaction, surveillance, image and film
processing and criminal identification [11]. Different
illumination, size and orientation of face image can be
effected the face recognition results. An input image is
captured by web camera at different illuminations with
different contrast may consists of shadows and high
darkness region. Human face have variety of emotions with
different expressions are more sensitive to different
conditions such as variation in illumination, noise, colors etc
[18]. Facial expressions recognition is a challenging task.
There is various subspace methods are defined such as PCA,
LDA, SVD. LPP, ICA used for feature extraction [2].
2. EXISTING VOTING SYSTEM
Current voting system is based on ballot machine where
when we press the button with the symbol the voting is
done. Here there is a security risk, the person who votes may
be fake person voting. The people there might not know
that a person is using fake voting card, this may cause
problem. Also the person who has to vote should travel from
faraway places to his constituency to cast his vote. So,
effective method is to use face detection while voting online
and enabling the right person to vote.
3. PROPOSED VOTING SYSTEM
In this study Face Detection and Recognition system is
proposed and it used as an authentication technique in
voting, application based voting allows the voter to vote
from any place in state or out of state[ 15]. The voter‟s
image is captured and passed to a face detection algorithm
like Haar like feature which is used to detect human face
from the image and save it as the first matching point. We
implement eigenface algorithm to recognize the trained
images stored in the database. The goal is to implement the
system model for a particular face and distinguish it from a
large number of stored faces with some real-time variations
as well. eigenface gives us efficient way to find the lower
dimensional space. Choosing the threshold value is a very
significant factor for performance of face identification in
eigenface approach. Besides that, the dimensional reduction
of face space relies upon number of eigenfaces taken. In this
research paper, an enhanced solution for face recognition is
given by taking the enhanced value of threshold value and
number of eigenfaces.
4. FACE DETECTION TECHNIQUE
Fig 1 Data Flow Diagram for the proposed voting system

_______________________________________________________________________________________
In the above flow diagram the captured image will be
detected using Haar-like feature algorithm and recognized
using Eigen face algorithm. This test image and the trained
image in the database will be compared. Simultaneously the
ID(aadhar number) is entered. Once entered number is
matched with the number in the Database and after the
matching of the image the image in the Database is will be
retrieved and the details of the voter will be displayed and
the candidate form will be enabled. Then the voter will be
allowed to vote. If the face is not matched or the ID is
invalid the voter will not be able to cast his/her vote.
Fig 2. Data flow diagram for Haar-like features
In the above flow diagram the input image (captured image)
is taken and sum of the pixels of the image is calculated.
Then from the entire image, rectangular node is selected
covering only the face. Each vertices of the rectangle is
named as A, B, C, D. Then the Haar-like feature calculation
is done by finding the difference of the sum of the adjacent
points(vertices).
i.e Sum= I(A) + I(C) – I(B) – I(D)
Then the trained image stored in the database using Haar-
like feature is compared with the test image selected using
Haar-like feature. If the comparison is true then the face is
detected else we need to select the different rectangle node
from the face of the captured image.
Object Detection using Haar feature-based cascade
classifiers is an effective object detection method proposed
by Paul Viola and Michael Jones in their paper, “Rapid
Object Detection using a Boosted Cascade of Simple
Features” [6]. It is a machine learning based approach where
a cascade function is trained from a lot of positive and
negative images. It is then used to detect objects in other
images.
Here we will work with face detection. Initially, the
algorithm needs a lot of positive images (images of faces)
and negative images (images without faces) to train the
classifier. Then we need to extract features from it. For this,
Haar features shown in below image are used. They are just
like our convolution kernel. Each feature is a single value
obtained by subtracting sum of pixels under white rectangle
from sum of pixels under black rectangle.
Fig 3 Land marks of extraction of features
For each feature calculation, we need to find sum of pixels
under white and black rectangles. To solve this, they
introduced the integral images. It simplifies calculation of
sum of pixels, how large may be the number of pixels, to an
operation involving just four pixels. In an image, most of the
image region is non-face region. So it is a better idea to have
a simple method to check if a window is not a face region. If
it is not, discard it in a single shot. Don‟t process it again.
Instead focus on region where there can be a face. This way,
we can find more time to check a possible face region.
5. FACE RECOGNITION TECHNIQUE
The scheme is based on an information theory method that
decomposes face images become a minute set of
characteristic feature images are called „eigenfaces‟, which
are in fact the principal components of the primary training
set of face images. The eigenface method is one of the most
efficient and simplest approaches in developing a system for
Face Recognition. The recognition is performed by
projecting new image into the subspace extended by the
eigenfaces („face space‟) and then organizing the face by
contrasting its position into the face space with the positions
of the identified individuals [2]. In eigenface method, the
distance is measured between couples of images for
recognition after the dimensional reduction of the face
space. If the distance is less than a certain threshold value,
then it is considered as an identified face else it is an
unidentified face [5].
In the figure 4, we have two set of image blocks training set
image block and test set image block. In training set image
block, firstly the Eigenface of image in the database (trained
image) is obtained. Then the weight W1 is calculated by
using the Eigenface and the training set. In the testing set
image block, input unknown image X which is the captured
image is taken. The weight W2 is calculated using the input
image and the Eigenface. Value of D is calculated by
finding the average of distances between W1 and W2. If the

_______________________________________________________________________________________
D value is less than 0, then the face is recognized. Then the
input image X and W2 values are stored. If the D value is
greater than 0, then the face is not recognized.
Fig 4. Data flow diagram for the Eigenface algorithm for
face recognition
6. RESULTS AND DISCUSSIONS
The experimental results are demonstrated in this paper to
verify the viability of the proposed face recognition method.
Also only 15% of eigenfaces with the largest eigenvalues
are adequate for the recognition of a person. The best
optimized solution for face recognition is provided when
both the features are combined i.e. 15% of eigenfaces with
largest eigenvalues are chosen and threshold value is chosen
0.8 times maximum of minimum the Euclidean distances
from all other images of each image, it will wholly improve
the recognition performance of the human face up to 97%.
Initially multi views of a voter/person face is captured with
webcam and voter details are entered with an appropriate
address, date of birth, aadhar card number then it is trained
and stored in a database, A Person who wants to vote should
correctly focus his/her face in front of webcam window then
enter the aadhar card id number. After doing this if voter
face and aadhar card id number match with the data base
value then voter is successfully complete voting.
Fig. 5 Training process under different views of a person
Fig. 6 Trained database images (Detected face of My
database)
Fig. 7 Testing process when person comes for voting.
Fig 8 Matching images with different facial expressions
7. CONCLUSIONS
This voting system helps everybody to cast their votes
without any problem. Voting application will increase the
percentage of voting. Manual counting is not required. So by
this we will get the very prominent, clear and fast result. By
using this newly developed system we can overcome many
problems of existing system. This system is more efficient
than the existing one. Application voting allows the voter to
vote from anywhere in his state or out of state.
We have used Face Detection and Recognition based on
Haar-like features and Eigen face recognition as
authentication in the application. This system detect the face
from an image captured using a webcam and recognize face
from AADHAR database and check if the two images
match. If a match accrues, then verify that the law and roles
of voting are not violated then allow him to vote.

_______________________________________________________________________________________
REFERENCES
[1] A. Hadid, “The local binary pattern and its
applications to face analysis,” in Proc. Int.Workshops
Image Process. Theor., Tools Appl., 2008, pp. 28– 36.
[2] Bhumika G. Bhatt , Zankhana H. Shah Face Feature
Extraction Techniques: A Survey National
Conference on Recent Trends in Engineering &
Technology 2013
[3] B. Froba and A. Ernst, “Face detection with the
modified census transform,”in Proc. IEEE Int. Conf.
Autom. Face Gesture Recog., 2004, pp. 91–96.
[4] Chennamma, H. R., Ragrajan, L., Rao, M. S.
Robustnear-duplicate image matching for digital
image forensics. International Journal of Digital
Crime and Forensics, 2009, vol. 1, no. 3, 18 p.
[5] Eric Hess „‟Facial recognition: A valuable tool for
Law Enforcement‟‟, Forensic magazine, Vol.7/ No.5,
November 2010. S.Ravi, S.Wilson, “Face detection
with facial features and gender classification based on
support vector machine”, 2010 IEEE Internation al
Conference on Computational Intelligence and
computing Research, ISBN: 97881 8371 362 7
[6] HE, R., ZHU, Y.A hybrid image segmentation
approach based on Mean Shift and fuzzy C –
means.In Asia – Pacific Conference onInformation
Processing.[Online] 2009.
[7] H.A. Rowley, S. Baluja, and T. Kanade, Neural
Network Based Face Detection, IEEE Trans. On
Pattern Analysis and Machine Intelligence, Vol. 20,
1998.
[8] H C VijayLakshmi, S. Patilkulkarni,, Face Detection
Algorithm for Skintone Images using Robust Feature
Extraction in HSV Color Space IJCA Special Issue
on “Recent Trends in Pattern Recognition and Image
Analysis" RTPRIA 2013
[9] J. Ruiz-del-Solar and J. Quinteros, “Illumination
compensation and normalization in eigenspace-based
face recognition: A comparative study of different
pre-processing approaches,” Pattern Recog. Lett., vol.
29, no. 14, pp. 1966–1979, 2008.
[10] K. Sung and T. Poggio, Example-based Learning for
View-based Human Face Detection, A.I. Memo 1521,
MIT A.I. Laboratory, 1994.
[11] Miss.Renke Pradnya Sunil Automatic Face
Recognition Using Principle Component Analysis
with DCT, Journal of Electronicsl and
Communication Engineering (IOSR-JECE-2013)
ISSN: 2278- 2834- , ISBN: 2278-8735, PP: 01-07.
[12] Reza Azad , Fatemeh Davami, A robust and
adaptable method for face detection based on color
probabilistic estimation technique, International
Journal of Research in Computer Science, ISSN
2249-8265 Volume 3 Issue 6(2013) pp. 1-7
www.ijorcs.org, A Unit of White Globe Publications
doi: 10.7815/ijorcs.36.2013.072
[13] Muralidharan, R., Chandashekar, C. Combining local
and global feature for object recognition using SVM-
KNN. In Proceedings of International Conference on
Pattern Recognition.Informatics and Medical
Engineering. 2012, ISBN 978-1-4673- 1039-0/12
[14] M. Pietik¨ainen, T. Ojala, and Z. Xu, “Rotation-
pnvariant texture classification using feature
distributions,” Pattern Recog., vol. 33, pp. 43–52,
2000.
[15] Noha E. El-Sayad, Rabab Farouk Abdel-Kader Face
Recognition as an Authentication Technique in
Electronic Voting, (IJACSA), Vol. 4 No. 6, 2013
[16] Mohamed A. Berbar ,Hamdy M. Kelash, and Amany
A. Kandeel, Faces and Facial Features Detection in
Color Images, Proceedings of the Geometric
Modeling and Imaging― New Trends (GMAI'06) 0-
7695-2604-7/06 $20.00 © 2006 IEEE
[17] Mrs.Smita Patil Prof. Mrs. A. A. Junnarkar,
Overview of Colour Image Segmentation Techniques,
IJARCSSE Volume 3, Issue 9, September 2013,
ISSN: 2277 128X
[18] Nikita Sharma, D.S.Singh, A Survey on various
Feature Extraction Techniques for Face Recognition,
IJCA, ISSUE 2, Volume 4 (August 2012) ,ISSN:
2250-1797, Page 18
[19] Roopashree.S, Sachin Saini, Rohan Ranjan Singh.
Enhancement and Preprocessing of Images using
filtering, IJEAT, ISSN:2249-8958 Volume-1 Issue-5,
June 2012 .
[20] TusharGajame, C.L. Chandrakar Face Detection with
Skin Color Segmentation & Recognition using
Genetic Algorithm International Journal of
Innovative Technology and Exploring Engineering
(IJITEE) ISSN: 2278-3075, Volume-3, Issue-2, July
2013

Real time voting system using face recognition for different expressions and pose variations

More Related Content

What's hot (20)

Viewers also liked (10)

Similar to Real time voting system using face recognition for different expressions and pose variations (20)

More from eSAT Publishing House (20)

Recently uploaded (20)

Real time voting system using face recognition for different expressions and pose variations