1 ABSTRACT

In this project a new authentication technique in online voting system using facial recognition of
the voter is used. In India, currently there are two types of voting system in practice. They are
secret Ballet paper and Electronic Voting Machines (EVM), but both of the process have some
limitation or demerits. In India online voting has not been yet implemented. The current voting
system is not safe and secure too. The voters need to go to distributed places like polling booths
and stand in a long queue to cast their vote, because of these reasons most of the people misses
their chance of voting. The voter who is not eligible can also cast its vote by fake means which
may leads to many problems. That’s why in this project we have to propose a system or way for
voting which is very effective or useful in voting. In our approach we have three level of security
in voting process.

The first level is the verification of unique id number (UID), second level is the verification of
election id number (EID) and third level is face recognition or face matching. The security level
of our system is greatly improved by the new application method for each voter. The user
authentication process of the system is improved by adding face recognition in an application
which will identify whether the particular user is authenticated user or not.
 2. INTRODUCTION

Now a day in India two types of method are used for voting. [1] The first method is secret ballot
paper, in which lots of paper are used and [2] second method is EVM (electronic voting
machine) which is used since 2003. we have to propose a method or way for online voting that is
more secure than the existing system. In this proposed project face detection and recognition
concept is used to identify the exact person. There are three levels of verification were used for
the voters in our proposed system. The first one is Unique id number verification, second level of
verification is election commission id or voter card number, if your election commission id
number is correct then you have to go for third level of security which is the main security level
where the system recognize the face of the real voter from the current database of face images
given by the election commission. If the captured image is matched with the respective image of
the voter in the database, then a voter can cast their vote in the election.as you have to know that
in existing system is not much more secure because in existing system security level is only voter
card so any one can give other person vote with voter card but here we proposed a way for
voting which is more secure than existing system.

In democratic societies, voting is an important tool to collect and re-act people‘s opinions.
Traditionally, voting is conducted in centralized or distributed places called voting booths..

Voting machines are the total combination of mechanical, electromechanical, or

electronic equipment (including software, firmware, and documentation required to program
control, and support equipment), that is used to define ballots; to cast and count votes; to report
or display election results; and to maintain and produce any audit trail information. The first
voting machines were mechanical but it is increasingly more common to use electronic voting
machines.

A voting system includes the practices and associated documentation used to identify
system components and versions of such components; to test the system during its development
and maintenance; to maintain records of system errors or defects; to determine specific changes
made after initial certification; and to make available any materials to the voter (such as notices,
instructions, forms, or paper ballots).
 Traditionally, a voting machine has been defined by the mechanism the system uses to
cast votes and further categorized by the location where the system tabulates the votes.oting
machines have different levels of usability, security, efficiency and accuracy. Certain systems
may be more or less accessible to all voters, or not accessible to those voters with certain types
of disabilities. They can also have an effect on the public's ability to oversee elections.

In this project we are working with three differentdifferent security levels Level1: -Unique id
number (UID) [4]. At the time of voter registration system will request for the unique id from the
voter. The entered unique id is verified from the database provide by the election commission.
Level2: Election commission id card number. [5] In the second level of verification, the voter
has to enter the election commission id or voter’s id number. The entered id number is verified
from the database provide by the election commission. Level3: - Face recognition with
respective election commission id number. In this level, Eigen face algorithm is used to verify
the facial image of the voters from the database provided by the election commission.

FACE RECOGNITION

A facial recognition system is a computer application for automatically identifying or

verifying a person from a digital image or a video frame from a video source. One of the ways to
do this is by comparing selected facial features from the image and a facial database. It is
typically used in security systems and can be compared to other biometrics such as fingerprint or
eye iris recognition systems.

The most popular approaches to face recognition are based on shape of facial attributes,
such as eyes, eyebrows, nose, lips, chin and the relationships of these attributes. All these
attributes of the face image are shown in figure 1.1.

Figure 1.1 Face Images

 As this technique involves many facial elements; these systems have difficulty in
matching face images. The face recognition systems which are used currently impose a number
of restrictions on how facial images are obtained. This face recognition system automatically
detects the correct face image and is able to recognize the person.

The face of a person has a numerous distinguishable characteristics. Face IT has 80 nodal
points and some of these points can be measured by software:

 Distance between eyes

 Width of the nose

 Depth of the eye sockets

 The shape of the cheekbones

 The length of the jaw line

By measuring these nodal points a special numeric code is created. This code is called a
face print, and it is this code that represents the face in the database.

EIGEN FACE ALGORITHM:

The main concept of Eigen Face algorithm is to follow the appearance –based approach to face
recognitio. It is used to capture the variation in a collection of face images and this information is
use to encode the particular images of individual faces. Then the encoded images of individual
faces are compared with the collection of face images in a holistic manner. The Eigen faces itself
form a basis set of all images used to construct the covariance matrix. The formed smaller set of
basis images are used to represent the original training images which produces dimension
reduction. By comparing how faces are represented by the basis set, the classification can be
achieved. Face Images are projected into a feature space (“Face Space”) that best encodes the
variation among known face images. The face space is defined by the “eigenfaces”, which are
the eigenvectors of the set of faces.
LEVEL 2

Smart Voting System Support through Face Recognition doesn’t fully show the all the
equipment that are to be connected to raspberry pi, but covers all major functional units. The IR
frames are connected over mirror but still they work fine because it’s a co-ordinate based touch
detection by the IR sensors placed at the side of frames and doesn’t require the frame to be
directly having contact with monitor behind mirror. The microphone is connected via sound card
on USB port of Pi. The camera can be connected to USB port or the Pi camera can be connected
to camera slot on Pi. The 8-channel relay is connected to GPIO pins on Pi for controlling the
home appliances. To access the internet the Pi is connected to home Wi-Fi network. The
programming of the Pi for displaying the UI on the screen is done using Python, the total
description of how coding is implemented is described in Section 3 of the document.

WORKING OF EIGEN FACE ALGORITHM:

Steps in Face Recognition

•Initialization: Acquire the training set and calculate Eigen faces (using PCA projections) which
define Eigen space.

• When a new face is encountered, calculate its weight.

• Determine if the image is face.

•If yes, classify the weight pattern as known or unknown.

• (Learning) If the same unknown face is seen several times incorporate it into known faces.
Principal Component Analysis

•Eigen face follows the Principal Component Analysis approach, in which face space forms a
cluster in image space
1) Every New User in the India is first register for Voting. So, our first step is registration

2) At that time of Registration System Capture, the Face of the user by using Web Camera and
Store the Face sample in the Server Database for Security Purpose.

3) At the time of election, we will use three level of security first one is unique id verification
second one is voter id verification third one is face recognition.

4) System will be checking whatever unique id and voter id entered by the voter is correct or not.

5) If unique id or voter id is correct than system will take image of voter and compare with the
respective image of database or server.

6) If the image in database is matching with the captured image of the voter, then he/she is
allowed to cast is vote.

7) On the voting page all the party whatever party contest in the election symbols /buttons will
be there. Voter can cast his /her vote in the election.

8) As soon as voter will give vote the id of voter logout automatically so we can say that a voter
can give only one vote.

9) On counting form only election commission authorized user can login with the secure id and
password if both id and password is correct then voting process will be continuing.
STEPS OF WORKING FLOW

Smart Voting System

1. Every New User in the India is first register for Voting. So, our first step is registration
2. At that time of Registration System Capture, the Face of the user by using Web Camera and
Store the Face sample in the Server Database for Security Purpose.
3. At the time of election, we will use three level of security first one is unique id verification
second one is voter id verification third one is face recognition.
4. System will be checking whatever unique id and voter id entered by the voter is correct or
not.
5. If unique id or voter id is correct than system will take image of voter and compare with the
respective image of database or server.
6. If the image in database is matching with the captured image of the voter, then he/she is
allowed to cast is vote.
7. On the voting page all the party whatever party contest in the election symbols /buttons will
be there. Voter can cast his /her vote in the election.
8. As soon as voter will give vote the id of voter logout automatically so we can say that a voter
can give only one vote.
9. On counting form only election commission authorized user can login with the secure id and
password if both id and password is correct then voting process will be continuing

3 LITERATURE SURVEY
Talking about the related work . I have been able to collect some of the papers, with the
methodology the authors have used as follows:

Since, Voting is a vital part of the democratic processes as such, the efficiency,
reliability, and security of the technologies involved is critical. Traditional voting technologies
include hand-counted paper ballots. These paper-based systems can result in a number of
problems, including:

 Unacceptable percentages of lost stolen or miscounted ballots

 Votes lost through unclear or invalid ballot marks.

 Limited accommodations for people with disabilities.

Today, the development and widespread use of information technologies is changing the way
people view voting processes and, ultimately, the way they vote. At the forefront of these new
technologies is Electronic Voting Machine (EVM).

There are several benefits of using EVM like reduced cost, increased participation and voting
options, greater speed and accuracy placing and tallying votes, greater accessibility for the
disabled, flexibility etc. But EVM can also results in problem like booth capturing. By booth-
capturing, if one means, taking away or damaging of ballot boxes or ballot papers, this evil
cannot be prevented by the use of EVMs, as EVMs can also be forcibly taken away or damaged
by miscreants. Another problem which results is that old age peoples need to be queued, waiting
for their turn to vote [3].

Computer scientists who have done work in, or are interested in, electronic voting all
[1]
seem to agree on two things : Internet voting does not meet the requirements for public
elections. Currently, widely-deployed voting systems need improvement [7].

Voting on the Internet using every day PC's offers only weak security, but its main
disadvantages are in the areas of anonymity and protection against coercion and/or vote selling.
The Presidential elections of 2000 brought national attention to problems with current American
methods of casting and counting votes in public elections [6].
 Most people believe that the current system should be changed; there is much
[3].
disagreement on how such changes should be made The MIT/Caltech researchers see a
promising future for electronic voting, despite its problems today (under a few conditions).

They advocate using the methods currently in use which results in the lowest average
numbers of “uncounted, unmarked, and spoiled ballots, like in-precinct optical scanning. Their
report even proposes a framework for anew voting system with a decentralized, modular design
[4].

One of the advantages of electronic voting is that, in most cases, most ballots will be
tabulated into the results. Paper-based voting machines can actually miss ballots because of
human error in placing the paper-based ballot in the machine. Another advantage is obviously
the ease of tabulating the results. All counting and ordering is done by a machine, quickly and
efficiently, and without human error. DRE voting machines also have the advantage of never
running out of paper ballots at a polling centre, since the computer can count an unlimited
number of ballots. They also can provide multiple languages to users who may not have English
as a first language. This cannot be achieved through a paper-based system.

There are also advantages when dealing with people with disabilities, such as blindness.
Electronic voting machines can provide headphones to read off instructions to the blind user.
Also other tools can be added to these electronic voting machines to help with other disabilities
such as people with limited mobility or the elderly.

Location-free Voting System with the help of IOT Technology The proposed concept uses
fingerprint sensor of the smart phone to cast the vote of the voter. An application must be
installed on the voter’s smartphone. This application is used to identify the fingerprint. Smart
phone’s fingerprint sensor is linked with the provided application to identify the uniqueness of
the original voter. Security provided is medium. This proposed system allows the voter to cast
their votes only on the day of Election. The voters are not be able to cast the vote other than the
day of Election. On the day of voting, voter scans their fingers along the fingerprint sensor of the
smartphone. Accuracy depends on fingerprint sensor of the mobile phone. Detection of fraud is
one of the core components of this system. It avoids casting of multiple votes by any voter.
Electoral voting systems provides facility to voters so that they are able to vote from any location
without any geographical restrictions all over the world which considers mobility, privacy,
security, and easiness. Current voting systems provided all over the world have similar problems
in each of them. The main concept in this paper is to provide a voting system that uses smart
phone’s fingerprint sensors in order to identify genuine voter and provide high accuracy,
security, and mobility to make voting system more practical and location-free.

Smart Electronic Voting System Based On Biometric Identification-Survey In this paper,

author defines Use of GSM (Global System for Mobile Communication) module in order to
enhance the speed and provide high security of the voting system. Using GSM module, the
message will be passed to the voter’s mobile mentioning that he has successfully casted his vote.
Using IOT the counted votes can be easily sent to the total database server so that all of the
counted votes and the elected party that has been selected can be announced easily. For avoiding
misconceptions during elections, many advanced techniques are being proposed using different
methods. But in the field of biometric identification, we can get the better results and it is also
trustworthy. This system works on the basis of master-slave server. We are able to transfer the
voted data online to the MASTER server unit. According to the proposed concept, number of
slave systems are kept at various locations. All the slave system are coupled to the nearest
Master System. This system is able to identify if a particular person has already casted their vote
or not. If a person has casted his vote earlier then a mechanism is set to buzzer the alarm and the
message displaying error appears and he is not able to cast the vote so that we are able to prevent
misconceptions during elections. This paper provides the various works which are being
proposed based on the voting system which uses biometric identification as a major concept.
Some other works have different algorithms being used and some other works have different
techniques provided are based on the multimodal biometric identification.

Secure Reliable Multimodal Biometric Fingerprint and Face Recognition In this paper the
author focuses on Image scanned for faces at different resolutions in a hierarchical face detector.
Hierarchical system is a component-based face detector which precisely localizes the faces and
extracts the components. The extracted components are merged into a single feature vector and
then fed to the face recognizer. This proposed approach has been implemented in MATLAB.
MATLAB has been implemented here because it is user friendly and it consists a number of
libraries which is currently being used. Implementation of this procedure results in the accurate
recognition of face, more over the time complexity is very less and the total cost required for this
implementation is very less, the juvenile facial analysis can also be possible. This can be adopted
in commercial or law enforcement departments in future. Biometric image recognition is the
process of studying the closest match region in between the examining images. The study of the
recognition is done about the spatial pixels (picture element) among the image. Recognition of
two different biometric features, finger print and face images are attempted. Finger print images
are analyzed through every available pixel. And face images are analyzed on the basis of
distance between various face mark identities and their relational distance difference. In this
paper we have used principal component analysis which completely out forms standards
technique and curve let transform. In the multi modal biometric technique, it is able to achieve
good results with all security system for finger print and face recognition.

Anti-Cheating Presence System Based on 3WPCADual Vision Face Recognition This paper
focuses on a face recognition method using half-join normalization with dual vision camera as a
face image acquisition tool and using 3WPCA(Three level Wavelet Decomposition-Principal
Component Analysis) as its feature extraction. Use of Dual vision camera has been able to
provide detectable face images from two different positions of the left and right lens. Image
retrieved from the two corners of the left lens and the right lens can provide a merged face image
in database combining left lens face image and right lens face image. The use of two sides of the
face angle is used to avoid fake facial data such as the use of a photo of a person or an image
similar to a person's face. This research can produce a presence system based on good face
recognition and can be used to identify dummy face data with its recognition accuracy up to
98%.

E-Smart Voting System with Secure Data Identification using Cryptography In this paper
the author focuses on the strategy used and functions of E smart voting system (ESVS) which is
very much secured, biometric authentication system which is provided with verification system
based on OTP that also improves the voting process in the time of election. The vote casted by
the user is first encrypted and then stored in the database. In this concept Aadhar number of user
is used for verification and identification of the voter. With smart voting system, voter is able to
cast their vote with their mobile phone and avoid all kind of queues at polling booth. At first,
Aadhar number is provided by the voter in the ESVS. The ESVS then uses the Aadhar number to
authenticate the user through OTP which will be received on their registered Aadhar linked
mobile number. People without Smart phones are also able to cast their vote through ESVS with
an additional step of authentication through highly secured Aadhar based biometric
authentication. Smart Voting System successfully allows people to vote through their smart
phones which helps to reduce the queues at the polling booth. Also, highly reliable biometric
authentication mechanism is provided for people who do not want vote using smart phones thus
prevent electoral fraud.

4APPLICATIONS

 It can be used to conduct general assembly elections.

  Fast track voting which could be used in small scale elections, like ‘resident welfare

association, panchayat level election’ and other society level elections.

 It can be used to conduct opinion polls during annual share holders meeting.

 It is used in various TV serials as for public opinion.

5 ADVANTAGES AND DISADVANTAGES

ADVANTAGES

 Low power consumption.

  Easy to implement.

 Cheap technology.

  Verification time is about five seconds.

 Very high accuracy.

 Easy to use

 High security

 More Reliability

 Scalability and flexibility.

DISADVANTAGES

 Requires special hardware.

 People feel inconvenience.

6 CONCLUSION

As we see that existing voting system has many defects such as lengthy process, time taking, not
secure, bogus voting, no security level but now we can say that our approach is more useful and
secure from the existing system. Since, we are using three level of security in this proposed
system the false voters can be easily identified. The facial authentication technique is very much
useful in identifying the fraud voters, so we can avoid the bogus votes during election
commission. The voters can cast their voting from anywhere by login to our proposed smart
voting system through internet. As every operation is performed through internet connectivity so,
it is onetime investment for government. Voters’ location is not important but their voting is
important. As data is stored in centralized repository so, data is accessible at any time as well as
backup of the data is possible. Smart voting system provides updated result at each and every
minute. Also requires less man power and resources. The database needs to be updated every
year or before election so that new eligible citizens may be enrolled and those who are dead are
removed from the voter list

REFERENCES
[1].Cetinkaya O and Cetinkaya D, “Towards Secure E-Elections in Turkey: Requirements and
Principles”, International Workshop on Dependability and Security in e-Government
(DeSeGov’07) – In Proceedings of ARES’07, Vienna, Austria, pp. 903-907, 2007.

[2].Benoit, D. K, “Experience with voting overseas”, Appendix 2J to the first report of Ireland’s
Commission on Electronic Voting, 2004.

[3].Jefferson, D.R., Rubin, A.D., Simons, B., and Wagner, D. () A "Security Analysis of the
Secure Electronic Registration and Voting Experiment (SERVE)"
www.servesecurityreport.org/ , 2004.

[4].Kohno T, Stubblefield A, Rubin AD, & Wallach DS. , “Analysis of an electronic voting
system”. IEEE symposium on security and privacy, 2004.

[5].Gritzalis D, editor. “Secure electronic voting. Advances in information security”, Kluwer

Academic Publishers, vol. 7, 2002.

[6].Hoffer J. A., George J & Valacich J, “Modern Systems Analysis & Design” 3rd edition,
Prentice Hall, Upper Saddle River, NJ, 2002.

[7].Caltech-MIT, “Voting: what is,what could be.Cal Tech-MIT Voting technology Project
Report”. www.vote.caltech.edu/ Reports, 2001.

[8].Benaloh, J. and Tuinstra, D. “Receipt-free Secret-Ballot Elections”, In Proceedings of the

26th ACM Symposium on Theory of Computing (STOC’94), Montreal, Canada, pp. 544-
553, 1994.

[9].Fujioka, A., Okamoto, T. and Ohta, K, “A Practical Secret Voting Scheme for Large Scale
Elections”, Workshop on the Theory and Application of Cryptographic Techniques - In
Proceedings of Auscrypt’92, Gold Coast , Australia, pp.244-251, 1992.
1. Pandit, Varad, Prathamesh Majgaonkar, Pratik Meher, Shashank Sapaliga, and Sachin
Bojewar. "Intelligent security lock." In Trends in Electronics and Informatics (ICEI), 2017
International Conference on, pp. 713-716. IEEE, 2017.

2. Chauhan, C. U., Abhishek Kalnawat, Akshay Aswale, Ujwal Gautam, and Roshan Nemad.
"Survey Paper on a Novel Approach: Web Based Technique for Vote Casting." International
Journal of Engineering and Management Research (IJEMR) 7, no. 5 (2017): 71GER, BARRY.
"CONTENTIOUS POLITICS AND URBAN DESIGN: TOWARD A NEW
ARCHITECTURAL THEORY." International Journal of Architecture and Urban Studies
(2017): 18

4. Sundaram, Ravi. "The Postcolonial City in India. From Planning to Information?." Techniques
& Culture. Revue semestrielle d’anthropologie des techniques (2017).

5. Warghade, Shrikant Subhash, and B. Karthikeyan. "Voting System for India." In Intelligent
Embedded Systems, pp. 59-65. Springer, Singapore, 2018.

6. Shah, Syed Afaq Ali, Uzair Nadeem, Mohammed Bennamoun, Ferdous Sohel, and Roberto
Togneri. "Efficient image set classification using linear regression based image reconstruction."
arXiv preprint arXiv:1701.02485 (2017).

7. Bhimanwar, Chinmay, Rupesh Biradar, Nikhil Bhole, and Milind Rane. "Face Identification."
International Journal of Engineering Science 11923 (2017).

8. Bhukuth, Augendra, Jérôme Ballet, and Isabelle Guérin. "Social capital and the brokerage
system: the formation of debt bondage in South India." Journal of Economic Studies34, no. 4
(2007): 311-323