AUTOMATED ATTENDANCE SYSTEM USING FACIAL

RECOGNITION
A PROJECT REPORT

Submitted by

VICTOR CHINNAPPAN S
(421123107053)
STANLEY JEBAKUMAR D
(421123107049)
VICTTOR G
(421123107054)
in partial fulfillment for the award of the degree

of

BACHELOR OF TECHNOLOGY
IN
ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING

IFET COLLEGE OF ENGINEERING

(An Autonomous Institution)
VILLUPURAM 605108
 NOVEMBER 2024

IFET COLLEGE OF ENGINEERING

(An Autonomous Institution)

BONAFIDE CERTIFICATE

Certified that this report titled “EYE BLINK SENSOR ” is the bonafide work of
VICTTOR G [421123107054], VICTOR CHINNAPPAN S [421123107053],
STANLEY JEBAKUMAR [421123107049] who carried out work under my
supervision. Certified further, that to the best of my knowledge the work reported here in
does not form part of any other basis of dissertation on the basis of which a degree or award
was conferred on an earlier.

SIGNATURE SIGNATURE
Mrs. S. USHARANI, ME,Ph.D Ms. D.SHANMUGAPRIYA(M.Tech)
HEAD OF THE DEPARTMENT SUPERVISOR

Associate Professor, Assistant Professor,

Department of AI & ML, Department of AI & ML,

IFET College of Engineering, IFET College of Engineering,
Villupuram – 605108 Villupuram – 605108

Submitted for the End Semester examination held on _____________________

 INTERNAL EXAMINER EXTERNAL EXAMINER

CERTIFICATE OF EVALUATION

College name : IFET College of Engineering, Villupuram.

Branch : B.Tech – Artificial Intelligence & Machine Learning
Month & Year : November 2024
Sub. Code & Name : 23PL3003/PRODUCT DEVELOPMENT LAB III

Name of the Supervisor With

Name of the Register Number Title of the Project Designation
students
VICTOR 421123107053 AUTOMATED Ms.SHANMUGAPRIYA D
CHINNAPPAN S
ATTENDANCE Assistant Professor
SYSTEM USING
STANLEY 421123107049
JEBAKUMAR D FACIAL
RECOGNITION
VICTTOR G 421123107054

The report for the Product Development Laboratory submitted for the fulfilment of the
award of the degree of Bachelor of Technology in Artificial Intelligence and Machine
Learning of IFET College of Engineering (Autonomous), permanently affiliated to Anna
University was evaluated and confirmed to be the work done by the above student.
 ACKNOWLEDGEMENT

We thank the almighty, for the blessings that have been showered upon me to bring
forth the success of the project. We would like to express my sincere gratitude to our
Chairman Mr.K.V.Raja, Secretary Mr.K.Shivram Alva and our Treasurer Mr.R.Vimal
for providing us with an excellent infrastructure and necessary resources to carry out this
project and we extend our gratitude to our principal Dr.G.Mahendran, for his constant
support to our work.

We also take this opportunity to express our sincere thanks to our Dean Academics
Dr.kanimozhi who has provided all the needful help in executing the project successfully.

We wish to express our thanks to our Head of the Department, Mrs.S.Usharani, for
her persistent encouragement and support to complete this project.

We express my heartfelt gratitude to my guide Ms.D.Shanmugapriya Department

of Artificial Intelligence and Machine Learning for her priceless guidance and motivation
which helped us to bring this project to a perfect shape.

And we thank our faculty advisor Ms.D.Shanmugapriya, Assistant Professor,

Department of Artificial Intelligence and Machine Learning who encouraged us in each and
every step of this project to complete it successfully.

We also thank our lab technicians and all the staff members of our department for their
support and assistance.

Last but not the least, we wholeheartedly thank my family and friends for their moral
support in tough times and their constructive criticism which made me succeed in our work.
 TABLE OF CONTENTS

CHAPTER TITLE PAGE NO

NO.

ABSTRACT 6

LIST OF ABBREVIATIONS 7

8
LIST OF FIGURE

1. 9
INTRODUCTION
1.1 OVERVIEW
1.2 SCOPE OF THE SYSTEM
1.3 OBJECTIVES
LITERATURE SURVEY 11
2. 2.1 RELATED WORK

13
3. PROPOSED SYSTEM

4. SYSTEM ARCHITECTURE
4.1 HARDWARE COMPONENTS 14
4.2 SOFTWARE COMPONENTS

5. CONCLUSION & FUTURE WORK

18

6. REFERENCE
19
 ABSTRACT

The automated attendance system using facial recognition is designed to streamline

and enhance the process of tracking attendance in educational institutions, workplaces, and
other settings. By leveraging advanced computer vision techniques and machine learning
algorithms, the system can accurately identify and verify individuals based on their facial
features. This system addresses the limitations of traditional attendance methods, which
are often time-consuming, prone to errors, and susceptible to manipulation.

The core of the system involves capturing real-time video or images of individuals as they
enter a designated area. These images are processed using OpenCV to detect faces, and
further analyzed using Convolutional Neural Networks (CNNs) to perform facial
recognition. Each detected face is compared against a pre-registered database of individuals
to verify their identity. Upon successful verification, the attendance record is automatically
updated in the system. Key features of the automated attendance system include real-time
detection and recognition, high accuracy and reliability, and the ability to handle large
datasets. The system can be integrated with IoT devices to enable remote monitoring and
management, and can also generate detailed attendance reports for analysis and record-
keeping

KEY WORDS:
Automated Attendance, Facial Recognition, Facial Recognition,
OpenCV, High Accuracy, Data Analysis, Educational Institutions, Real-time
Detection, Facial Recognition
 LIST OF ABBREVIATIONS
IOT Internet of Things

AI Artificial Intelligence

OpenCV Open Source Computer Vision

ML Machine Learning

CV Computer Vision

API Application Programming Interface

GUI Graphical User Interface

DB Database

UI User Interface

UX User Experience

IoE Internet of Everything

LAN Local Area Network

Wi-Fi Wireless Fidelity

NLP Natural Language Processing

JSON JavaScript Object Notation

HTTPS HyperText Transfer Protocol Secure

 LIST OF FIGURE

FIGURE NO TITILE PAGE NO

4.1 ARCHITECTUR DIAGRAM 9

4.2 BLOCK DIAGRAM 10

4.3 CIRCUIT DIAGRAM 10

 CHAPTER I
INTRODUCTION

1. Overview

The automated attendance system using facial recognition aims to modernize and
streamline the process of tracking attendance in various settings. Utilizing a camera to
capture real-time images, the system employs machine learning models such as Haar
Cascades or CNNs to detect and recognize faces accurately. Each detected face is matched
against a pre-registered database to verify identity and mark attendance automatically. The
system updates attendance records in a database, ensuring accuracy and reducing manual
errors. Integration with IoT devices enables remote monitoring and management through an
intuitive dashboard. This technology enhances efficiency, security, and user experience,
making it ideal for schools, offices, and other organizations. The system is scalable and can
be expanded to accommodate more users as needed. It provides real-time data and detailed
reports for analysis and record-keeping. The solution is designed to comply with data
privacy regulations, ensuring the security of personal information. Overall, the project offers
a cutting-edge approach to attendance management, combining advanced technology and
user-friendly interfaces.

2. OBJECTIVE

Project Aim: The primary objective of this project is to develop an efficient and
automated attendance tracking system using facial recognition technology. The system aims
to replace traditional manual attendance methods with a modern, reliable, and secure
solution.
Specific Objectives:

1. Accuracy and Efficiency

2. Real-Time Processing
3. User-Friendly Interface
4. Integration with Existing Systems
5. Report Generation
1.3 SCOPE OF THE STUDY

The scope of this study on the automated attendance system using facial recognition covers
several critical areas that underline the project's significance and potential impact. It includes
the technological implementation, which integrates hardware components like cameras and
Raspberry Pi, along with software libraries such as OpenCV and dlib for efficient face
detection and recognition. The study focuses on improving efficiency and accuracy in
attendance tracking, reducing manual errors, and saving time through automated processes.
It also examines the data management capabilities of the system, particularly its ability to
securely store and retrieve attendance records using an SQLite database. Additionally, the
study assesses the user experience by evaluating the system's usability for administrators and
users, ensuring a user-friendly interface and providing real-time updates. Furthermore, it
identifies future enhancements, including advanced facial recognition algorithms and the
development of a mobile app for broader application, making the system more versatile and
accessible. This comprehensive approach highlights the potential of facial recognition
technology in transforming traditional attendance systems.
1. Technological Integration: Implementation of hardware like cameras and
Raspberry Pi with software libraries such as OpenCV and dlib.
2. Efficiency Improvement: Enhances attendance tracking efficiency by reducing
manual errors and automating processes.
3. Accuracy Enhancement: Improves accuracy in attendance records through
advanced face detection and recognition algorithms.
4. Data Management: Secure storage and retrieval of attendance records using an
SQLite database.
5. User Experience: Evaluation of the system's usability and interface design for
administrators and end-users.
 CHAPTER II
LITERATURE SURVEY

Journal Articles on Facial Recognition in Attendance Systems

Early Techniques and Foundations:

[1] Tittle: Face Recognition Using Eigenfaces

1. Authors: M. Turk, A. Pentland

2. Year: 1991

3. Journal/Conference: Journal of Cognitive Neuroscience

4. Summary: Introduced the PCA-based Eigenfaces technique for facial recognition. It laid
the groundwork for modern facial recognition systems.

[2] Tittle: Fisherfaces for Robust Face Recognition

1. Authors: P. Belhumeur, J. Hespanha, D. Kriegman

2. Year: 1997

3. Journal: IEEE Transactions on Pattern Analysis and Machine Intelligence

4. Summary: Proposed the use of LDA (Fisherfaces) for better recognition under varying
lighting and facial expressions.

Machine Learning-Based Approaches:

[1] Tittle: A Comparative Study of SVM and k-NN for Face Recognition
1. Authors: S. Shah, R. N. Dave
2. Year: 2014
3. Journal: International Journal of Computer Applications
4. Summary: Compared the performance of machine learning algorithms like SVM and k-
NN for facial recognition tasks.
[2] Tittle: Enhancing Attendance Management Systems Using ML

1. Authors: K. Sharma, V. Agarwal

2. Year: 2018

3. Journal: International Journal of Advanced Research in Computer Science

4. Summary: Discussed the integration of ML models into real-time attendance systems to

improve efficiency.

Deep Learning-Based Systems

[1] Tittle: DeepFace Closing the Gap to Human-Level Performance in Face

Verification

1. Authors: Y. Taigman, M. Yang, M. Ranzato, L. Wolf

2. Year: 2014

3. Journal: IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

4. Summary: Introduced the DeepFace model, one of the first deep learning models to

achieve near-human accuracy.

[2] Tittle: FaceNet A Unified Embedding for Face Recognition and Clustering

1. Authors: F. Schroff, D. Kalenichenko, J. Philbin

2. Year: 2015

3. Journal: CVPR

4. Summary: Poposed a face embedding system that maps faces into a high-dimensional

space for recognition and clustering

 CHAPTER III
PROPOSED SYSTEM

The proposed system automates attendance management using facial

recognition technology, offering an efficient and reliable alternative to
traditional methods. It employs hardware components such as cameras for
capturing real-time images and a processing unit like Raspberry Pi or Arduino
Uno for handling facial recognition tasks. The system uses pre-trained deep
learning models like FaceNet or DeepFace to identify and verify individuals
accurately. Once a face is recognized, attendance is marked automatically,
and the data is securely stored in a local or cloud-based database. This process
eliminates manual errors, saves time, and prevents proxy attendance, making
it an ideal solution for classrooms, workplaces, and other environments.

This system is scalable, user-friendly, and non-invasive, with the ability

to handle large groups and pvide real-time attendance tracking. It also
generates detailed analytics for monitoring attendance patterns. However,
environmental factors such as lighting or occlusions can impact recognition
accuracy, and privacy concerns must be addressed with robust data protection
measures. Despite initial setup costs for advanced hardware, the system's
long-term benefits, including reduced manual effort and increased reliability,
make it a practical and modern solution for attendance management.
 CHAPTER IV
SYSTEM ARCHITECTURE
The system architecture for the automated attendance system using facial recognition is
designed to work efficiently with both hardware and software components. A camera is
used to capture real-time images or videos of individuals. Optional motion sensors or IoT
devices can activate the camera when someone is detected. These images are then sent to
a processing system where the faces are detected using methods like Haar cascades or
advanced deep learning techniques.
Once a face is detected, it is analyzed using models such as FaceNet or DeepFace to
extract unique facial features. These features are compared with stored data in a database
to identify the person. If a match is found, the system records their attendance along with
the date and time. The attendance records are saved in a database, either locally or in the
cloud, and can be accessed through a simple interface for viewing or generating reports.
This architecture makes attendance management fast, reliable, and easy to use.

Fig:4.1 Architecture Diagram

4.1 Hardware Components:

Core Components:
Camera Module (Camera or USB Webcam):
1. Captures real-time video feed of the classroom environment.
2. Sends the video feed to the Raspberry Pi for processing using computer vision
algorithms.
Raspberry Pi (Model 4B or 3B+):
[1] Acts as the central processing unit (CPU) of the system.
[2] Executes pre-trained machine learning models (face detection, emotion recognition,
engagement analysis).
[3] Processes real-time video data and computes engagement levels.
Power Supply:
[1] Provides power to the Raspberry Pi and connected peripherals like the camera, LEDs,
and buzzer.

FIGURE4.2 CIRCUIT DIAGRAM

4.2 Software Components:

Programming Platform:
[1] Python: Programming language for writing the main script.
[2] OpenCV: Library for image processing and face detection.
[3] dlib: Library for facial landmark detection and recognition.
[4] Face Recognition Library: Simplifies implementation of face recognition.
[5] SQLite: Database for storing attendance records.
[6] MQTT Library (paho-mqtt): For data transmission to IoT devices.

Python Programming:
[1] Controls the Raspberry Pi hardware components (camera and display).
[2] Implements AI/ML processing and outputs results in real time.

Optional Cloud Storage (AWS/Firebase):

[1] Stores engagement analytics for future review by teachers and administrators.
[2] Allows access to historical engagement data for performance improvement.

FIGURE:4.3 BLOCK DIAGRAM

Advantages of the Architecture
The automated attendance system using facial recognition offers numerous advantages,
making it a highly efficient and reliable solution for attendance management. It
significantly reduces the time required for attendance compared to traditional methods by
automating the process of recognition and logging. The system ensures high accuracy in
identifying individuals, minimizing errors and preventing manipulation or proxy
attendance. Its user-friendly interface eliminates the need for manual record-keeping,
providing a seamless experience for users and administrators alike. With real-time
monitoring, attendance data is updated instantly, enabling quick decision-making and
instant access to records. Enhanced security is achieved through biometric identification,
ensuring that only authorized individuals are marked present, reducing the risk of
unauthorized access or fraud.

The system also excels in data management, allowing efficient storage, retrieval, and
generation of reports for analyzing attendance patterns over time. It is highly scalable,
supporting the addition of new users and expansion to larger areas, making it suitable for
diverse environments like schools, offices, and events. Integration with IoT devices further
enhances functionality, enabling remote monitoring and alerts. While the initial
implementation costs may be higher, the system becomes cost-effective over time by
reducing administrative workload and operational expenses. Additionally, it supports
compliance with regulatory requirements for attendance tracking and provides detailed
reports for auditing and record-keeping, ensuring a comprehensive and modern approach
to attendance management.
 CHAPTER V

CONCLUSION
The automated attendance system using facial recognition stands as a
testament to the power and potential of integrating advanced technology with everyday
processes. By leveraging facial recognition algorithms and IoT capabilities, this system offers
a modern solution that is efficient, accurate, and user-friendly. It significantly reduces the
time and effort required for manual attendance tracking, minimizes errors, and enhances
security through biometric identification. The system's scalability ensures it can be adapted
for various applications, from educational institutions to corporate offices and beyond. With
real-time monitoring and robust data management, organizations can benefit from detailed
attendance reports and insights, aiding in better decision-making and resource management.
As technology continues to evolve, this system can be further enhanced with more advanced
features, ensuring it remains at the forefront of innovation. Overall, the automated attendance
system using facial recognition is a forward-thinking approach that improves efficiency,
accuracy, and security in attendance management, meeting the needs of modern
organizations.

FUTURE WORK:
In the future, this system can be expanded with advanced capabilities such as
predictive analytics, where machine learning models could forecast attendance trends and
identify potential absenteeism patterns based on historical data. This would enable proactive
measures to address attendance issues before they escalate. Integrating voice recognition and
sentiment analysis could provide additional insights into student engagement and well-being,
further refining the monitoring process.
Support for multilingual interfaces and accessibility features for students with disabilities
could enhance inclusivity, making the system adaptable for diverse classroom
environments. Deploying cloud computing could significantly improve scalability, allowing
seamless integration across multiple classrooms or institutions. As educational institutions
continue to embrace digital transformation, the smart attendance system using Raspberry Pi.
and facial recognition will evolve as a pivotal tool in creating efficient, secure, and inclusive
learning environments, empowering both educators and students for long-term success
 CHAPTER VI

REFERENCES

[1] A. Ahmedi and S. Nandyal, “An Automatic Attendance System Using Image
processing,” pp. 1–8, 2015..

[2] V. Shehu and A. Dika, “Using real time computer vision algorithms in automatic
attendance management systems,” Inf. Technol. Interfaces (ITI), 2010 32nd Int. Conf.,
pp. 397–402, 2010.

[3] J. Joseph and K. P. Zacharia, “Automatic Attendance Management System Using Face
Recognition,” Int. J. Sci. Res., vol. 2, no. 11, pp. 327–330, 2013.

[4] J. Kanti and A. Papola, “Smart Attendance using Face Recognition with Percentage
Analyzer,” vol. 3, no. 6, pp. 7321–7324, 2014.

[5] P. Mehta, “An Efficient Attendance Management Sytem based on Face Recognition
using Matlab and Raspberry Pi 2,” Int. J. Eng. Technol. Sci. Res. IJETSR, vol. 3, no. 5,
pp. 71–78, 2016.

[6] Yusuf Perwej , Firoj Parwej, Asif Perwej, “Copyright Protection of Digital Images Using
Robust Watermarking Based on Joint DLT and DWT ”, International Journal of
Scientific & Engineering Research (IJSER), France, ISSN 2229-5518, Volume 3, Issue
6, Pages 1- 9, 2012

[7] Robert Schalkoff, Pattern Recognition Statistical Structural and Neural Approaches,
Wiley Student Edition

[8] Face Recognition using SURF algorithm by Roberto Morales Caporal, Federico Ramirez
Cruz conf. paper 2015