DEVELOPMENT OF AN AUTOMATED FACIAL RECOGNITION ATTENDANCE SYSTEM
Abstract
ABSTRACT
This project focuses on the development of an automated facial recognition attendance system
aimed at improving the accuracy, speed, and reliability of student attendance tracking. Manual
attendance methods are often time-consuming, error-prone, and susceptible to impersonation.
In many institutions, attendance is still recorded manually, leading to inefficiencies and delays.
By utilizing facial recognition technology, this system offers a contactless and efficient way of
recording attendance. Unlike traditional systems whether manual or biometric methods such as
fingerprint scanning that require physical contact or additional hardware, this approach is more
hygienic and suitable, especially in large educational settings. Despite technological
advancements, many schools still lack a fully automated and contactless attendance solution.
This project addresses that gap by developing a facial recognition system that marks attendance
without any physical interaction. The main objective of this study was to develop an automated
facial recognition attendance system linked to a database to record student attendance
effectively. The methodology involved collecting student data through a user interface that
allows students to register their faces. Additional information such as student names, course
registrations, email addresses, and phone numbers were also collected and stored in the
database. The user interface was designed using JavaScript and Bootstrap 5.3.3, while the
backend was developed using Django 4.2.15. Software requirements included Windows 10,
OpenCV (for facial recognition), and MySQL for managing student data. Hardware used
included a camera for face capture and recognition, an Intel Core i7 processor, and 8GB of
RAM. The developed system successfully detects and recognizes student faces in real time
with high accuracy. It eliminates the need for manual attendance, reduces time consumption,
and prevents impersonation. The performance evaluation results of the system are; for the
accuracy is 90.98%, the precision is 93.69%, the average confidence is 73.39% and lastly, for
the recall is 96.30%. The system is efficient, reliable, and suitable for educational institutions.
This project demonstrates how facial recognition technology can be effectively used to
automate attendance systems, offering a secure, fast, and user-friendly approach to attendance
management
Full-Text Access Notice
In accordance with the NERD Policy on promoting peer-reviewed publication, public access to the full text of a project, thesis or dissertation is restricted for three years, allowing the author and supervisors sufficient time to pursue peer-reviewed publication.
During this period, researchers with legitimate academic or research purposes may request authorisation directly from the author to enable NERD to release the indexed full texts of the work using the form below.