Development and Evaluation of a Facial Recognition-Based Computer Laboratory Attendance Monitoring System

Abstract

Managing student attendance efficiently is critical in modern academic settings, particularly in computer laboratories where time and access control are vital. This study developed a Computer Laboratory Attendance Monitoring System using facial recognition technology to automate, secure, and streamline attendance recording. The system employs cameras at laboratory entrances to capture real-time facial images, which are compared with a centralized database to record attendance automatically, thereby eliminating manual logging, ID card swiping, and reducing risks of proxy attendance and human error. The system was developed using the Rapid Application Development (RAD) methodology and evaluated using the ISO 9126 software quality model, focusing on functionality, reliability, usability, efficiency, maintainability, and portability. Key challenges included facial recognition accuracy under varying environmental conditions, hardware limitations, and user privacy concerns. These were addressed through improved machine learning models, data encryption, multiple image registration, and user training sessions. System evaluation involved 30 respondents, including students and IT professionals, yielding a grand mean rating of 4.2 (Strongly Agree) across all ISO 9126 quality attributes, indicating high user satisfaction and acceptance. Findings suggest that the proposed system provides a reliable, user-friendly, and scalable solution for attendance management in academic institutions, with potential for broader adoption across multiple laboratories or campuses.