Fingerprint Based Voting

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 09 Issue: 04 | April 2022 www.irjet.net p-ISSN: 2395-0072
© 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 622
Fingerprint Based Voting
Akshat Bheda1, Udit Intwala2, Rahul Ghimire3, Prof. Sanketi Raut4
,1,2,3 Student, 4Assistant Professor, Department of Information Technology Engineering, Universal college of
Engineering, Maharashtra, India
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - The idea of this paper arises by taking the
present Covid crisis into consideration, as public gathering is
prohibited/limited and risky. If people gather for voting in
such situations there it may give rise to vast spread of virus
instead of keeping it under control. People need to maintain
long queues which costs them a lot of time and energy. The
main motive of this project is to offer reliability and prohibit
the challenges that are in the conventional balloting system.
The simple idea of this project is the user has to register on the
app, submit their fingerprint which will be processed using
SIFT algorithm and complete theirvoting. So, by usingtheidea
of this project people can avoid long queues and also avoid
gathering and can vote easily from their homes without
risking their lives keeping the Covid crisis under control.
Key Words: Fingerprint, Voting, Java, Firebase, Python,
Android, SITF.
1.INTRODUCTION
These days the mechanical device has become an efficient
toll compared with traditional paper-based voting
techniques. Thus, we decided to style a system to beat the
already existing electoral system. the most scheme of this
project is to possess safer, no duplication of votes and
declare the results as early as possible.
Requirements are often classified into functional and
security requirements. Reviewing these requirements as
they affect e-voting system, the important factors are:
• Authentication
• Integrity
• Confidentiality
• Non-Repudiation
• Accuracy
• Flexibility
• Auditability
• Eligibility
2. LITERATURE SURVEY
We have studied some of available fingerprint recognition
system and how it can be implemented.
Biometric Based Mobile Voting
This paper shows various methods voting can be carried on
mobile devices. It creates simple application to perform
voting with help of biometric stored in government
database. Accessing it and basedonthatvotingiscarried out.
Fingerprint Recognition System: Design & Analysis
Fingerprint are of large variety. Some has more no of ridges
and curve than others, some individual has almost no
fingerprint. It is really important to design a system whichis
capable to counter almost all possible scenarios. There are
many techniques developed in recent years from optical to
ultrasonic fingerprint reader.
3. PROBLEM STATEMENT
Current system majority of them use ballot system with
digital system. A more hybrid method to ensure the votingis
done without cheat. It is said that no system is complete
system. Every system has major or minor flaw which is
exploit for unfair advantages. We cannot make a fully secure
system, if something is working it does not mean it can’t be
better.
Problem arise as such votingsystemneedseachindividual to
physically present at the time of voting. Which is true as to
conform identity, it is not possible always as many
individuals has to face difficulty especially for disabled
individual.
Also, at time when there is a global catastrophe where we
are prohibited to gather in crowd and perform mass voting.
This project is to tackle exactly such situations. It makes
voting literally at your doorsteps. Proposed system is
privacy protected authentication system in which database
of biometric identities is createdusingfingerprinttemplates.
4. IDEA OF IMPLEMENTATION
Fingerprint recognition system uses android camera to
capture image of voter’s finger and then pass it to the

database to match the fingerprints in order to authenticate
the voter.
It works along with built-in android biometrics
authentication to enhance the authentication of voting
system.
4.1 TECHNILOGY USED
4.1.1. Android Studio
Android Studio is an Integrated Development Environment
(IDE) for android app development, based on IntelliJ IDEA.
On top of IntelliJ’s powerful code editor and developer tools,
It offers many great features that help increase your
productivity while building android apps.
4.1.2. Java
Java may be a general-purpose, class-based, object-oriented
programming language designed for having lesser
implementation dependencies.Itisa computingplatform for
application development. Java is fast, secure, and reliable.
4.1.3. Firebase
Google Firebase may be a Google-backed application
development software that permits developers to develop
iOS, Android and Web apps. Firebase provides tools for
tracking analytics, reporting and fixing appcrashes,creating
marketing and merchandise experiment.
Firebase offers a number of services, following are used:
• Authentication, Realtime database, Firebase Storage,
Firebase Analytics
4.1.4. OpenCV
This paper describes a system createdusingSIFTtechnology
to identify fingerprint and with help of it we can verify user
fingerprint. It allows user to verified and authenticated.
It can be used and implemented in multiple ways, It provide
freedom to create dynamic system with solid security setup.
We can replace current version of working system to much
faster and more secure version.
4.1.5. Python
It is an interpreted high-level general-purposeprogramming
language. Its design philosophy emphasizescodereadability
with its use of serious indentation. Its language constructs
also as its object-oriented approach aim to assist
programmers write clear, logical code for little and large-
scale projects.
4.2 SYSTEM DESIGN
The motive of our system design is to create a procedural
solution that can fulfil thefunctional requirementsforsecure
scheme for e-democratic governance. The architecture that
describes the components and interfaces of the entire
system derived from system requirements are modelled to
solve identified problem.
Figure 1: System Design
The first part of this work is to create database of different
fingerprints of voter, who are eligible for voting in election.
Fingerprint sensor is used for scanning of finger and
generates the templates. After creating a database, the
complete process is classified in three parts.
First one is identification in which, fingerprint of the voteris
matched with the previously stored templates in database.
Second part is verification, in which whether the voter is
valid or not is to be checked. If one of the templates matches
with the finger of voter then, the voter is eligible for voting.
Repeated voting is also monitored in this process, which is
not allowed by the same candidate.
Third part of the work is voting, in which, voter will choose
the option, which is available for voting. This is developed
using java, python using android studio IDE.
4.3 ALGORITHM
4.3.1. SITF [5]
Scale Invariant Feature Transformation (SIFT). The SIFT
algorithm proposed by Lowe[1] is an approach for extracting
distinctive invariant features from images. It has been
successfully applied toa spreadofcomputervisionproblems
supported feature matching, which incorporates visual

perception, pose estimation, image retrieval, etc. Since the
SIFT feature points have already showed their efficacy
within the visual perception field, there are high expectation
to be used in fingerprint verification.
This method extractsdistinctivefeaturesfromimages,which
can be used to perform reliable matching between different
images. There are four major stages of computation usedfor
generating the SIFT features: Scale-spaceextrema detection,
Key point localization, Orientation assignment and the Key
point descriptor.
4.3.2. Implementation
The Process start with taking clear image of voter
fingerprint, it is then stored into firebase with respect to the
authenticated voter.
After performing voting the voter will submit his fingerprint
which is send to algorithm, It then access stored fingerprint
image from the firebase database storage.
It then performs matching of fingerprint as follows:
1. Taking Initial Fingerprint image:
(sample = cv2.imread("Input Image"))
2. Taking Stored Fingerprint image from Database:
(for [file stored in Database (“Image from
Database")]
3. Extracting Keypoints from both the images:
(keypoints_1,descriptors_1=sift.detectAndCompute(
sample, None)
keypoints_2,descriptors_2=sift.detectAndCompute(f
ingerprint_image, None))
4. Matching and Comparing Key points of both images:
(matches1=cv2.FlannBasedMatcher({'algorithm':1,
'trees': 10}, {}).knnMatch(descriptors_1,
descriptors_2, k=2)
bf = cv2.BFMatcher(cv2.NORM_L1,
crossCheck=False)
matches=bf.match(descriptors_1,descriptors_2)
matches = sorted(matches, key=lambda x:
x.distance)
for p, q in matches1:
if p.distance < 0.1 * q.distance:
match_points.append(p)
keypoints = 0
if len(keypoints_1) < len(keypoints_2): keypoints =
len(keypoints_1)
else: keypoints = len(keypoints_2))
5. Displaying result with best possible match:
(print("BEST MATCH: " + filename)
print("SCORE: " + str(best_score))
result = cv2.drawMatches(sample, kp1, image, kp2,
mp, None)
plt.rcParams['figure.figsize'] = [14.0, 7.0]
plt.title('Best Matching Points') plt.imshow(result)
plt.show())
4.3.3. Result
Figure 2: Test 1 Image Output
Figure 3: Test 1 Output

Figure 4: Test 2 Output
Fingerprint Test Table
Fingerprints Result %
Fingerprint 1 Fingerprint 2 82.65
Fingerprint 1 None No Match
5. CONCLUSIONS
This paper describes a system createdusingSIFTtechnology
to identify fingerprint and with help of it we can verify user
fingerprint. It allows user to verified and authenticated.
It can be used and implemented in multipleways, itprovides
freedom to create dynamic system with solid security setup.
We can replace current version of working system to much
faster and more secure version.
REFERENCES
[1] David G. Lowe, “Object recognition from local scale-
invariant features”, International Conference on
Computer Vision, Corfu, Greece, pp. 1150- 1157, 1999
[2] D.G.Lowe, “Distinctive Image Features from Scale-
Invariant Keypoints,” International Jounal of Computer
Vision, 60(2), 91-110, 2004
[3] P. Gnanasivam, S. Muttan, “An efficient Algorithm for
fingerprint preprocessing and feature extraction”
Procedia Computer Science 2 (2010) 133–142.
[4] Donovan Gentles, Dr. Suresh SankaranarayananAdjunct
Professor, “Biometric Secured Mobile Voting” 2011
IEEE.
[5] Ru Zhou, SangWoo Sin, Dongju Li, Tsuyoshi Isshiki and
Hiroaki Kunieda, “Adaptive SIFT-Based Algorithm for
Specific Fingerprint Verification” 2011 IEEE.
[6] Kavita Rathi and Sudhir Sawarkar, “Finger Print
Matching Algorithm for Android” International Journal
of Engineering Research & Technology (IJERT) ISSN:
2278-0181 Vol. 2 Issue 10, October – 2013.
[7] G.A. Bahgat, A.H. Khalil, N.S. Abdel Kader, S. Mashali,
“Fast and accurate algorithm for core point detection in
fingerprint images”Egyptian InformaticsJournal (2013)
14, 15–25
[8] Dibyendu Nath, Saurav Ray, Sumit Kumar Ghosh,
“Fingerprint Recognition System: Design & Analysis”
Conference Paper · January 2011 Research Gate 2014.
[9] Masao Yamazaki, Dongju Li, Tsuyoshi Isshiki and
Hiroaki Kunieda, “SIFT-based Algorithm for Fingerprint
authentication on smartphone”. 2015 IEEE.
[10]Farah Dhib Tatar, “fingerprint recognition algorithm”
David C. CCSEIT, AIAP, DMDB, ICBB, CNSA – 2017.
[11]Khadija Hasta, Aditya Date,Aparna Shrivastava,Prajakta
Jhade, S. N. Shelke, “Fingerprint Based Secured Voting”.
[12]Noorazlina Mohamid Salih, “A Design of Voting System
by Using an Android Apps for Fisherman.

Fingerprint Based Voting

More Related Content

Similar to Fingerprint Based Voting (20)

More from IRJET Journal (20)

Recently uploaded (20)

Fingerprint Based Voting