A Face Recognition-Based System for Monitoring Examination Attendance: A Case Study in a Tertiary Institution

Abstract

The increasing demand for reliable and efficient attendance tracking during examinations in tertiary institutions has highlighted the limitations of traditional manual systems. These systems are often prone to inaccuracies, time consumption, and security breaches such as impersonation. This study presents the design and implementation of a Face Recognition System for Examination Attendance (FRSEA), developed to automate and enhance the accuracy of student verification during exam sessions using advanced deep learning models, such as Convolutional Neural Networks (CNNs) the system captures and analyzes facial features in real-time to identify students against a pre-registered database. The architecture comprises three layers—presentation, application, and database—and integrates hardware components like high-resolution cameras with intelligent software algorithms to ensure high recognition accuracy, even in challenging conditions. The system’s features include real-time face detection, scalable database management, and strict security protocols to safeguard biometric data. Through rigorous unit, system, and user testing, the FRSEA demonstrated significant improvements in speed, reliability, and fraud prevention compared to conventional methods. This paper concludes that face recognition technology provides a practical and scalable solution for enhancing examination attendance systems in higher education, while also emphasizing the importance of privacy, usability, and continuous optimization.