Report: Fingerprint and Face Authentication Portable Digital Electronic Voting Machine

Fingerprint and Face Authentication

Portable Digital Electronic Voting
Machine
by John Bacus

General metrics
25,692 3,871 223 15 min 29 sec 29 min 46 sec
characters words sentences reading speaking
time time

Score Writing Issues

99 50 9 41
Issues left Critical Advanced

This text scores better than 99%

of all texts checked by Grammarly

Plagiarism
This text hasn’t been checked for plagiarism

Report was generated on Wednesday, Jul 26, 2023, 04:46 PM Page 1 of 27

Report: Fingerprint and Face Authentication Portable Digital Electronic Voting Machine

Writing Issues
13 Clarity
4 Wordy sentences
5 Unclear sentences
4 Intricate text

24 Engagement
24 Word choice

12 Correctness
2 Wrong or missing prepositions
2 Determiner use (a/an/the/this, etc.)
1 Misspelled words
1 Text inconsistencies
1 Improper formatting
1 Punctuation in compound/complex
sentences
3 Confused words
1 Closing punctuation

1 Delivery
1 Tone suggestions

Unique Words 21%

Measures vocabulary diversity by calculating the unique words
percentage of words used only once in your
document

Report was generated on Wednesday, Jul 26, 2023, 04:46 PM Page 2 of 27

Report: Fingerprint and Face Authentication Portable Digital Electronic Voting Machine

Rare Words 43%

Measures depth of vocabulary by identifying words rare words
that are not among the 5,000 most common English
words.

Word Length 5.3

Measures average word length characters per word

Sentence Length 17.4

Measures average sentence length words per sentence

Report was generated on Wednesday, Jul 26, 2023, 04:46 PM Page 3 of 27

Report: Fingerprint and Face Authentication Portable Digital Electronic Voting Machine

Fingerprint and Face Authentication

Portable Digital Electronic Voting
Machine

Fingerprint and Face Authentication Portable Digital Electronic Voting Machine

Brandon Sage Cagape

College of Engineering Education
Electronics Engineering Program
University of Mindanao, Davao City, Philippines
b.cagape.513587@umindanao.edu.ph
John Carlo Lisondato
College of Engineering Education
Electronics Engineering Program
University of Mindanao, Davao City, Philippines
johncarlolisondato1@gmail.com
Princess Diane Maboloc
College of Engineering Education
Electronics Engineering Program
University of Mindanao, Davao City, Philippines
dianemaboloc@gmail.com

John A. Bacus*
College of Engineering Education
Computer Engineering Program

Report was generated on Wednesday, Jul 26, 2023, 04:46 PM Page 4 of 27

Report: Fingerprint and Face Authentication Portable Digital Electronic Voting Machine

University of Mindanao, Davao City, Philippines

john_bacus@umindanao.edu.ph

Abstract—The paper presents the Electronic Voting Machine (EVM) device to

1
facilitate digital elections with the use of Raspberry Pi as its brain. The EVM is
designed to authenticate the voter through fingerprint or face authentication.
The face authentication method is incorporated with an anti-spoofing
technique. Local Binary Pattern Histograms (LBPH) and Haar-Cascade
Classifier models were used to detect and recognize faces and eye-blink
counters for anti-spoofing. Both authentications were combined and
incorporated into the voting graphic user interface (GUI), programmed through
Python and its libraries to create the EVM, wherein the voter must authenticate
through fingerprint or face recognition if they failed the prior method. The
accuracy tests resulted in an overall 80% and 95.56% accuracy for fingerprint
and face authentication, respectively. The anti-spoofing technique resulted in
an overall accuracy of 100%. The mock elections of 20 voters conducted to test
the functionality of the EVM resulted in an 80% fingerprint authentication
success rate, while 100% of the remaining 20% passed the face
authentication. Those who failed the fingerprint authentication proceeded to
face authentication, resulting in an overall 100% success rate in the
authentication of all voters. The database results matched the receipt of the
voters, demonstrating the device's overall efficiency of 100%. In conclusion,
the paper proposes an efficient and secure EVM that ensures fair and
transparent digital elections.
Keywords— Electronic Voting Machine, Local Binary Pattern Histogram (LBPH),
Haar-Cascade Classifier, Anti-Spoofing, Raspbian OS, FirebaseDB

Report was generated on Wednesday, Jul 26, 2023, 04:46 PM Page 5 of 27

Report: Fingerprint and Face Authentication Portable Digital Electronic Voting Machine

Introduction
2
Voting is one of the fundamental rights that an individual possesses as an
essence of democracy. It gives them the freedom to choose candidates they
think are most suited to represent the people and their interests. Among the
different voting systems in the world, the Philippines has adopted the Paper
Ballot system wherein the voters shade the circle beside the candidate's name
on the ballots provided to them and are then fed into a machine that will count
3
their votes. This system is good to some extent; however, there are
disadvantages. One is the possibility of ghost voting and the production and
use of defective ballots, marked as wastage. Despite the number of faulty
4
ballots being a small percentage overall, this percentage is still significant,
especially in small-scale voting [1]. This wastage can be avoided by investing in
Electronic Voting Machines (EVM). The other disadvantage of the Paper Ballot
system is that it is susceptible to fraud. There is an issue in the recent
Philippine Presidential Elections in which most voters were advised to
voluntarily surrender their ballots to the poll watchers as the machine that is
5
supposed to read their ballots is under repair. Even if there are no reported
fraudulent activities, it is still possible; therefore, switching to fully automated
voting is advisable to prevent fraud [2]. The Paper Ballot system can also hinder
the voting ability of marginalized population, such as the illiterate, [pregnant]
women, Persons with Disabilities (PWDs), and senior citizens, since the voting
interpretation and validity is left at the discretion of election officers.
Electronic Voting Machines will prevent this, ensuring their votes are correctly
counted [3]. Aside from significantly reducing electoral costs, tackling
fraudulent activities, and ensuring the participation of the marginalized
population, using EVMs will also make vote counting quicker since the results

Report was generated on Wednesday, Jul 26, 2023, 04:46 PM Page 6 of 27

Report: Fingerprint and Face Authentication Portable Digital Electronic Voting Machine

are declared within 2-3 hours compared to the paper ballot system, which
takes an average of 30-40 hours vote-counting time [4].
6
A study of [5] uses PIC16F877A as a microcontroller in an Electronic Voting
Machine, making the voting process faster, more reliable, and more efficient.
However, there is a problem with the fingerprint data since the database
images have high resolution requiring more memory to be allocated. There is
7
also an Arduino-based EVM that is particularly used in school elections. This
EVM is workable but not 100% efficient since it can only accommodate three
(3) candidates and has limited memory [6]. A face recognition feature is
commonly used in an Electronic Voting Machine to authenticate the user
registered on the server. In the case of twin voters, a two-fold biometric
authentication is used to avoid it [4]. In biometric testing of the study [7], the
parameters False Acceptance Rate (FAR) and False Reject Rate (FRR) are
applied. The FAR is an identification percentage used when there is an
unexpected acceptance of an unauthorized user, whereas the FRR is the
percentage of registered but rejected or unmatched users. Based on the
calculations, there is a FAR of 2%, an FRR of 10%, and an overall 94% high
accuracy indicating that the biometric is reliable for user authentication. The
OpenCV library is integrated and then executed by Python language. The Haar-
Cascade and Local Binary Pattern Histogram model is used for face detection
and recognition authentication [8]. Also, the use of Raspberry Pi 4 as the
8 9
processing unit in running the face recognition was conducted [9]. A certain
device with a face recognition feature that also uses Haar-Cascade has a 92%
accuracy in recognizing its subjects. The Local Binary Histogram (LPB)
algorithm resulted in an accuracy of 91%, which both accuracy rates are
considered high percentages [10]. One of the disadvantages of face recognition
features is that it is prone to identity fraud because of facial spoofing. Facial

Report was generated on Wednesday, Jul 26, 2023, 04:46 PM Page 7 of 27

Report: Fingerprint and Face Authentication Portable Digital Electronic Voting Machine

spoofing is using a person's face through a photo, a video, or a hyper-realistic

mask to steal their identity [11]. This act can be prevented by different anti-
spoofing techniques such as using sensors or dedicated hardware for detecting
facial features, challenge-response methods of the user in real-time and
recognition algorithms (specular feature projections, depth feature fusion,
image quality assessment, deep learning) [12].
The study focuses on an Electronic Voting Machine (EVM) with two
authentication methods for authentic, transparent, and credible voting
systems. Specifically, the EVM features biometric authentication combined
with face recognition authentication that will ensure the credibility of the
voting system [13]. To completely authenticate the user, an anti-spoofing
technique will be implemented together with face recognition to prevent
identity theft through facial spoofing. The technique that will be used is the
challenge-response technique, wherein the user is requested to interact with
the system in a specific way, such as doing facial expressions or head
movements [14]. An EVM is in the form of a portable standalone tablet kiosk for
convenience in voting. A receipt is printed after voting for the voters to ensure
10
that their votes are read correctly. The receipt will be put in a drop box, which
the committee keeps for manual recounting in case a candidate files a petition
for it [15].
This study aims to develop a standalone Electronic Voting Machine (EVM) with
two authentication systems. More specifically, this electronic voting machine
should be able to recognize and authenticate the fingerprints and faces,
supported by the anti-spoofing technique of the registered users as
implemented. This study also aims to perform an effective voting procedure
and accurately count the number of votes from the registered users and tally

Report was generated on Wednesday, Jul 26, 2023, 04:46 PM Page 8 of 27

Report: Fingerprint and Face Authentication Portable Digital Electronic Voting Machine

them. Furthermore, the votes counted from the system should match the
manual vote count from the receipts printed after the voting process.
This study would be of great importance as it will make voting more convenient
with the aid of a device that will make the flow of the electoral process
smoother. The Electronic Voting Machine (EVM) will be a standalone computer
kiosk to make the voting process ideal for the voters and will not be a hassle.
The monitor screen used for the voting process will have bigger fonts to make
the on-screen instructions very clear and readable for people, especially senior
citizens and those with poor eyesight. With this, they can vote with little to no
effort. The EVM will use fingerprint and face authentication features to ensure
the authenticity and credibility of the voting process. An anti-spoofing
technique with a face recognition feature will be implemented to prevent
identity theft through facial spoofing. This technique will also prevent fraud as
only the voter can access their registered account. Moreover, since the voter
will be the one to decide which fingerprint (left or right thumb, index, middle,
ring, pinky) they are to register with, they will also be the only ones aside from
the proponents who will know which one to use for their authentication. This
factor will add to the security of the EVM system.
This study proposes to create an Electronic Voting Machine that uses two
authentication methods, fingerprint and face recognition, to prevent fraud and
the possibility of ghost voting. Producing an EVM will also remove the need to
print out ballots where there is unavoidable production of defective ones. The
11
EVM will be set in a kiosk style similar to closed Automatic Teller Machine (ATM)
places, making it easy to navigate for first-time voters while giving them
enough privacy when voting. The only difference will be that the EVM kiosk will
be lower and table-like compared to the ATMs to cater to PWDs, especially
those in a wheelchair. This adjustment will also make the voters, especially the

Report was generated on Wednesday, Jul 26, 2023, 04:46 PM Page 9 of 27

Report: Fingerprint and Face Authentication Portable Digital Electronic Voting Machine

senior citizens, more comfortable when voting. As a limitation, blind people are
the only PWD excluded from being catered to because including them would
12
yield additional features to be considered, which would cause additional
expenses and complicated intricacies in the Electronic Voting Machine.
Compared to the usual voting system of the Philippines, using indelible ink
after voting will no longer be needed because the implementation is small-
scale; the system can check whether the individual has already voted.
13
Additionally, voter information and vote counts are saved on a cloud database,
presuming that there is a sudden and unprecedented data loss. A receipt will
be printed after voting for transparency and for the voters to ensure that their
14
votes are read correctly. The receipts generated will then be dropped in a drop
box and kept by the committee for manual recounting, especially when there
are anomalies or a candidate requests it. This aspect is another way of
preserving data in case of corruption or loss. This study aims to implement
small-scale voting, such as school body elections and vote-based contests,
using this Electronic Voting Machine (EVM). Specifically, the implementation
will occur at our university, The University of Mindanao.
Materials and Methods
Conceptual Framework
15
The study used Raspberry Pi as the main processing unit of the system, which
ran the Raspbian operating system. The component used was compatible with
the Adafruit fingerprint scanner through its USB. Also, the Python language was
used for programming because of its compatibility with the libraries used. The
Open Computer Vision Library, or OpenCV, was widely used for image
processing and computer vision projects. Additionally, the library was utilized
to build the Haar-Cascade model for face detection/anti-spoofing and LBPH

Report was generated on Wednesday, Jul 26, 2023, 04:46 PM Page 10 of 27

Report: Fingerprint and Face Authentication Portable Digital Electronic Voting Machine

(Local Binary Pattern Histogram) model for face recognition [8]. Aside from this,
the Pyqt5 library designed the system's graphical user interface (GUI).
Fig. 1 shows the conceptual framework of the study. The system required
fingerprint or face acquisition to validate the voter's identity for authentication,
16
which was the system's input. The fingerprint acquired was preprocessed to
optimize the sample and extract significant features to find the matched
fingerprint from the database [15-16]. If the system failed to authenticate the
registered voter's fingerprint, it proceeded to face authentication. The system
first performed face detection, increasing the face recognizer's accuracy since
it marked the voter's face before proceeding to recognition. Afterward, the face
recognition algorithm matched the extracted voter's face from the database.
17
Moreover, the same face detection algorithm was used for the anti-spoofing
procedure. It detected the voter's eyes and then required them to blink twice to
prevent identity theft. There were two authentication methods, but the voter
18
was only required to pass one of the biometric authentications before
proceeding to the voting proper, wherein the voter voted for their preferred
candidates among the selection and finalized their votes. Furthermore, this
comprised the electronic voting machine.

Conceptual Framework
Face Detection and Recognition Model

Report was generated on Wednesday, Jul 26, 2023, 04:46 PM Page 11 of 27

Report: Fingerprint and Face Authentication Portable Digital Electronic Voting Machine

Fig. 2 shows the overall concept of the Haar-Cascade classifier model. It used
Haar features to determine the lines or edges of the samples wherein there
were changes in the pixel intensity. It also used the integral images technique
to summate pixels over the image sub-area [10]. Aside from this, pre-trained
files were available to detect specific body parts like the face for face
detection. Eye detection requires the voter to blink their eyes to prevent anti-
spoofing.

Ha-ar Cascade Classifier

Fig. 3 illustrates the Local Binary Pattern Histogram or LBPH model, one of the
simplest algorithms used in facial recognition. The model located the image
structure and compared each pixel to its adjacent pixels. The adjacent values
were then converted to binary based on a threshold, where 1s represented
values above the threshold, while 0s represented values below the threshold.
The algorithm's accuracy was proportional to the number of samples in the
19
dataset, and a minimum of 100 samples was required to achieve optimal
accuracy [8]. In this study, 200 image samples were collected from each voter.

Report was generated on Wednesday, Jul 26, 2023, 04:46 PM Page 12 of 27

Report: Fingerprint and Face Authentication Portable Digital Electronic Voting Machine

LBPH (Local Binary Pattern Histogram)

Voter's Registration
20
Before the election day, people eligible to vote were registered ahead of time
with their personal information, which included their names and samples for
fingerprint and face recognition, the two methods of authentication for the
EVM. Furthermore, they were given informed consent regarding our study. As
shown in Fig. 4, voters must touch the fingerprint scanner with their desired
finger for authentication. The images were processed with a highly sensitive
pixel amplifier, then extracted templates that were stored/saved in the
database as a unique ID.

Report was generated on Wednesday, Jul 26, 2023, 04:46 PM Page 13 of 27

Report: Fingerprint and Face Authentication Portable Digital Electronic Voting Machine

Fingerprint Registration Block Diagram

In Fig. 5, 200 face images were collected from each voter using a camera. The
21 16
images were then pre-processed to provide good-quality images rather than
false ones. Next, feature extraction was implemented to extract the face
components. Lastly, images were trained by converting extracted features of
each image to binary, resulting in the center point being the decimal equivalent.
These significant features were the face encodings stored in pickle files used in
face recognition.

Face Registration Block Diagram

Voter's Recognition

Report was generated on Wednesday, Jul 26, 2023, 04:46 PM Page 14 of 27

Report: Fingerprint and Face Authentication Portable Digital Electronic Voting Machine

To be able to vote, one had to pass either fingerprint or face authentication. The
voter was to authenticate first through the fingerprint authentication method.
However, if the voter's fingerprint biometric is not recognized, they will be
22
redirected to face authentication instead. If the voter failed to authenticate
22
themselves from both methods, they could not proceed to the voting proper.
23
Fig. 6 shows the fingerprint and face recognition block diagram. This diagram
started when the voter touched the fingerprint scanner for authentication. If
successfully authenticated, the scanned fingerprint is enhanced through the
HSP amplifier and matched to the stored fingerprint data. Once a match was
found, the voter information was fetched from the database for authentication,
and then the recognized voter could proceed to the voting display.

Fingerprint and Face Recognition Block Diagram

When the voter fails to authenticate through fingerprint recognition, it will
proceed to face recognition. The voter's images were scanned, and their facial
features were extracted. The system then compared the sample image with the

Report was generated on Wednesday, Jul 26, 2023, 04:46 PM Page 15 of 27

Report: Fingerprint and Face Authentication Portable Digital Electronic Voting Machine

stored face encodings to determine the best match. If the sample image
matched the stored encodings, the voter's name was selected, and their
information was fetched from the database. The system then proceeded to the
voting display.
If the voter fails again to authenticate through face recognition, then the voter
will not be able to vote.
System Integration
The EVM and registration were separated, as shown in Fig. 7. A laptop was used
24
to collect voter data, including their names and authentication data. The
gathered data was sorted and transferred to the storage of the Raspberry Pi.
25
The transferred features were then used to authenticate the voters.
Additionally, the Internet of Things (IoT) database was used to store the users
26 26
who had already voted, together with their votes, in the Firebase database to
prevent data loss in case the Raspberry Pi storage gets corrupted. Additionally,
this cloud database only connected when the EVM validated the voter's
already-voted status or appended the recent voter and their vote selection.

System Integration
Hardware Development
Fig. 8 illustrates the prototype design of the Electronic Voting Machine. The size
and dimensions of the prototype were based on the needs and capacity of the
potential categories of voters. There was a presumption that one of the
27
potential categories of voters who would use the Electronic Voting Machine was

Report was generated on Wednesday, Jul 26, 2023, 04:46 PM Page 16 of 27

Report: Fingerprint and Face Authentication Portable Digital Electronic Voting Machine

Persons with Disabilities (PWDs), with the exclusion of blind voters [17]. The
Electronic Voting Machine was placed on a table so that it reached the height of
48" (~1.2m), which was the ideal height of an EVM according to the Kiosk ADA
Accessibility ADA Compliance for it to be accessible to the PWDs, especially the
people on a wheelchair like the disabled.

Electronic Voting Machine (EVM) Prototype Design

Statistical Analysis
This study employed two authentication methods to verify the legitimacy of the
voting process by conducting trials and calculating the overall accuracy for
fingerprint and face authentication using a confusion matrix. Furthermore,
28
precision, which measured the accuracy of positive predictions, recall, which
29
measured the ability of the model to identify positive cases, and F1 score,
which provided a balanced measure of both metrics, were computed.
Additionally, the False Reject Rate (FRR), the rate of registered voters that were
not authenticated, was compared to the precision. In contrast, the False
30
Acceptance Rate (FAR), the rate of unregistered voters authenticated with
31
another person's identity, was compared to the recall. Database vote selection
and voting receipt selection were compared.
Results and Discussions

Report was generated on Wednesday, Jul 26, 2023, 04:46 PM Page 17 of 27

Report: Fingerprint and Face Authentication Portable Digital Electronic Voting Machine

Electronic Voting Machine

32
Fig. 10 shows the actual device used to conduct the mock election with the
32
following components used: the monitor screen, mouse, camera, and thermal
printer, all of which were connected to the Raspberry Pi 4 to perform the voting
procedure.

Actual Device
Accuracy Testing Results
The accuracy test results for the fingerprint authentication are shown in Table I.
33
Fifteen (15) samples were tested, with three trials conducted for each sample.
The overall accuracy was calculated by taking the percentage average of the
34
three trials
35
Fingerprint Authentication accuracy test results

Based on the results, a low accuracy of 60% was observed in the first trial.
During the testing, some fingers sampled in the first trial had wet or dirty

Report was generated on Wednesday, Jul 26, 2023, 04:46 PM Page 18 of 27

Report: Fingerprint and Face Authentication Portable Digital Electronic Voting Machine

fingers, which caused them not to be recognized. After noticing the problem,
36
they clean their fingers, increasing accuracy in the next two trials.
The accuracy test results for face authentication are shown in Table II,
presented in a confusion matrix with two classifications: registered and
unregistered voters. Thirty (30) samples were used, with three trials conducted
37
for each sample.
38
Confusion Matrix For Face Authentication accuracy test results

Of the total trials for the registered voters, forty-five (45) were authenticated
(True Positive), and none (0) were rejected. On the other hand, of the total trials
for the unregistered voters, three (3) were falsely identified as other people
(False Negative), while forty-two (42) were classified as unknown (True
Negative).
From the accuracy testing, the face recognition algorithm had a confidence
value of 97%. The resulting confidence value of the registered voters ranged
from 98.09% to 99.82%, while the unregistered voters ranged from 89.98% to
97.98%. With this, the algorithm confidence level was tuned to 98.09, adjusted
from the lowest confidence value of the registered voters to prevent false
negative results on the actual mock election.

Report was generated on Wednesday, Jul 26, 2023, 04:46 PM Page 19 of 27

Report: Fingerprint and Face Authentication Portable Digital Electronic Voting Machine

The overall accuracy of the face authentication method is 95.56% using

equation (1). The precision and recall are 100% and 91.84% using equations (2)
and (3), respectively. Lastly, the F1-score resulting from equation (4) was
95.75%. Moreover, the False Rejection Rate (FRR) resulted in 0% using
39
equation (5), while the False Acceptance Rate (FAR) resulted in 8.16% using
40
equation (6).

Table III shows the overall accuracy of the anti-spoofing technique (blink twice)
41 41
used after a successful face authentication. The overall accuracy was
computed by the success count over the total number of trials in which the
result was 100%.
Anti-Spoofing Test Results

Mock Election Results

42
The results in Fig. 10 showed the type of authentication in which the voters
have successfully verified. It is marked as "Successful" if the voter has
43
authenticated in that authentication method, while an "Error" is marked when
the voter has failed to do so. In the case of the face authentication method, the

Report was generated on Wednesday, Jul 26, 2023, 04:46 PM Page 20 of 27

Report: Fingerprint and Face Authentication Portable Digital Electronic Voting Machine

voter is marked as "Passed" when it already has successfully authenticated

44
with their fingerprint, where they will no longer need to authenticate for their
face.
Based on the results, all voters were able to authenticate themselves
45
successfully. 16 out of 20 voters authenticated with their fingerprints, while 4
46
out of 20 voters had to go through face recognition to authenticate themselves.
47
The overall accuracy is computed by the percentage of the fingerprint and face
authentication method's success rate. Given this, the accuracy of fingerprint
and 0face authentication are 80% and 20%, respectively, which resulted in an
overall accuracy of 100%.
In addition, comparing the accuracy results of the fingerprint authentication to
the results of the prior accuracy testing, the authentication method also had
80% accuracy.

Fingerprint and Face Authentication Results

Database Votes and Receipt Votes Comparison
Based on the results in Fig. 11, all twenty (20) voters authenticated and
48
proceeded to the voting proper successfully. The candidates chosen by each
voter were stored in the EVM system, and the printed receipt containing the

Report was generated on Wednesday, Jul 26, 2023, 04:46 PM Page 21 of 27

Report: Fingerprint and Face Authentication Portable Digital Electronic Voting Machine

voter's name and selected candidates were dropped in the drop box after
confirming their selections. The casted votes stored from the database were
49
compared to the receipts, and as presented in Table V, all votes matched from
each other, resulting in an accuracy of 100%.
Database Votes and Receipt Votes Comparison

Conclusions and Future Works

A Raspberry Pi-based IoT portable electronic voting machine system was
successfully designed, incorporating fingerprint and face authentication
methods for voter identity verification. The Adafruit fingerprint sensor was
used for fingerprint authentication, achieving an overall accuracy of 80%. The
lower accuracy threshold was attributed to failed fingerprint detection in the
first trial, primarily due to wet or dirty fingerprints. Face authentication,
utilizing Haar-Cascade Classifier and Local Binary Pattern Histogram (LBPH)
models, achieved an overall accuracy of 95.56%. An anti-spoofing technique
ensured 100% accuracy in detecting and preventing spoofing attempts. While
the face authentication method successfully authenticated all registered
voters, a few unregistered voters were mistakenly recognized, resulting in a
False Acceptance Rate (FAR) of 8.16%. In a mock election with 20 registered
voters, 80% were authenticated using the fingerprint authentication method,
while the remaining 20% proceeded to face authentication and achieved 100%

Report was generated on Wednesday, Jul 26, 2023, 04:46 PM Page 22 of 27

Report: Fingerprint and Face Authentication Portable Digital Electronic Voting Machine

overall authentication accuracy. Vote results from the database and voter's
receipts matched with a 100% match for all 20 authenticated voters.
For future studies, the researchers recommend displaying the user interface
50
using a touchscreen LCD to reduce device bulkiness and facilitate easier GUI
navigation. Additionally, a more sensitive fingerprint sensor with a high
tolerance for wet or dirty fingerprints is suggested.

Report was generated on Wednesday, Jul 26, 2023, 04:46 PM Page 23 of 27

 Report: Fingerprint and Face Authentication Portable Digital Electronic Voting Machine

1. with the use of → using Wordy sentences Clarity

2. Voting is one of the fundamental rights Unclear sentences Clarity

that an individual possesses as an
essence of democracy.

3. good → suitable Word choice Engagement

4. ballots → votes Word choice Engagement

5. ballots → votes Word choice Engagement

6. of Wrong or missing prepositions Correctness

7. particularly → mainly Word choice Engagement

8. the face Determiner use Correctness

(a/an/the/this, etc.)

9. certain → particular, specific Word choice Engagement

10. receipt → ticket, token, pass, permit Word choice Engagement

11. kiosk style → kiosk-style Misspelled words Correctness

12. additional → other Word choice Engagement

13. Additionally → ¶ Additionally Intricate text Clarity

14. receipts → tickets, tokens Word choice Engagement

15. main → central Word choice Engagement

16. preprocessed; pre-processed Text inconsistencies Correctness

17. Moreover → ¶ Moreover Intricate text Clarity

18. required → needed, necessary Word choice Engagement

19. samples → pieces Word choice Engagement

Report was generated on Wednesday, Jul 26, 2023, 04:46 PM Page 24 of 27

 Report: Fingerprint and Face Authentication Portable Digital Electronic Voting Machine

20. the election Determiner use Correctness

(a/an/the/this, etc.)

21. images → photos Word choice Engagement

22. Tone suggestions Delivery

23. recognition block Improper formatting Correctness

24. was used to collect → Wordy sentences Clarity

collected

25. transferred → shared, assigned Word choice Engagement

26. Additionally, the Internet of Things (IoT) Unclear sentences Clarity

database was used to store the users
who had already voted, together with
their votes, in the Firebase database to
prevent data loss in case the Raspberry
Pi storage gets corrupted.

27. potential → possible Word choice Engagement

28. positive → optimistic Word choice Engagement

29. , and → ; and, . And Punctuation in Correctness

compound/complex
sentences

30. authenticated → Word choice Engagement

established, shown, certified

31. was → as Confused words Correctness

32. Fig. 10 shows the actual device used to Unclear sentences Clarity
conduct the mock election with the
following components used: the monitor
screen, mouse, camera, and thermal
printer, all of which were connected to
the Raspberry Pi 4 to perform the voting
procedure.

33. sample → Word choice Engagement

piece, model, example, instance

Report was generated on Wednesday, Jul 26, 2023, 04:46 PM Page 25 of 27

 Report: Fingerprint and Face Authentication Portable Digital Electronic Voting Machine

34. trials. Closing punctuation Correctness

35. Fingerprint Authentication accuracy test Intricate text Clarity

results

36. next → Word choice Engagement

following, subsequent, successive

37. sample → Word choice Engagement

piece, model, example, instance

38. Face Authentication accuracy test Intricate text Clarity

results

39. equation → Equation Confused words Correctness

40. equation → Equation Confused words Correctness

41. Table III shows the overall accuracy of the Unclear sentences Clarity
anti-spoofing technique (blink twice)
used after a successful face
authentication.

42. in which Wordy sentences Clarity

43. marked → observed, scored, celebrated Word choice Engagement

44. authenticate → show, establish Word choice Engagement

45. authenticated → shown Word choice Engagement

46. authenticate → establish, show Word choice Engagement

47. overall Wordy sentences Clarity

48. Based on the results in Fig. 11, all twenty Unclear sentences Clarity
(20) voters authenticated and proceeded
to the voting proper successfully.

49. from Wrong or missing prepositions Correctness

50. easier → more straightforward Word choice Engagement

Report was generated on Wednesday, Jul 26, 2023, 04:46 PM Page 26 of 27

Report: Fingerprint and Face Authentication Portable Digital Electronic Voting Machine

Report was generated on Wednesday, Jul 26, 2023, 04:46 PM Page 27 of 27