AI-Based Face Recognition Attendance Management System Using Python and Flask
Hosnain, Md.
Abstract
Attendance management plays an important role in educational institutions, offices, and organizations. Traditional attendance methods, such as manual registers, ID cards, and fingerprint devices, often require additional time and effort to maintain. These methods may also lead to issues such as proxy attendance, data inaccuracies, and administrative complexity. To address these challenges, this project presents the development of an AI-Based Face Recognition Attendance Management System using Python, Flask, OpenCV, and the Face Recognition library. The system is designed to identify registered individuals automatically through facial recognition technology and record attendance without requiring physical interaction. During the enrollment process, multiple facial images of an employee are collected and converted into facial embeddings. These embeddings are then used to recognize employees during real-time detection and attendance monitoring. The system also includes features such as employee management, attendance history, unknown face logging, live detection, and secure web-based administration. A web application was developed using the Flask framework to provide an easy-to-use interface for system administration. The solution was tested under different conditions, including varying facial expressions, lighting environments, and image sources. Experimental results demonstrated that the system can accurately recognize enrolled employees and maintain attendance records efficiently. The developed system offers a practical, low-cost, and contactless attendance solution that can be deployed in educational institutions, corporate offices, laboratories, and other organizational environments. It reduces manual effort, improves attendance accuracy, and enhances overall management efficiency.
Permanent link — send this address to others:https://lib.su.edu.bd/thesis/123456789/3061