Design and Development of Integrated Human Resource Management System with Face Recognition Attendance

Abstract

Workforce management is a critical function in any organization, yet traditional human resource practices and manual attendance tracking are often inefficient, error-prone, and insecure. This study proposes an integrated Human Resource Management System (HRMS) with a face recognition-based attendance tracking system to address these issues. The system was developed using ReactJS for the front end and implemented facial recognition through the YuNet model for face detection, the SFace model for facial feature extraction, and K-Nearest Neighbors (KNN) for classification. The research employed a true experimental design and evaluated the face recognition system using performance metrics such as False Acceptance Rate (FAR) and False Rejection Rate (FRR). Various normalization techniques were tested, with gamma correction yielding the most balanced performance, achieving a low FAR of 7.3% and an FRR of 46.7%. The system demonstrated efficient recognition performance and security, significantly reducing unauthorized access while maintaining reliable attendance logging. These results affirm the system’s potential to enhance HR operations through automation, accuracy, and a user-friendly interface.