Attendance Monitoring Using Multiple Face Recognition for Students

Attendance management is an important activity in educational institutions. Traditional attendance methods, such as calling student names or maintaining paper records, are time-consuming and may result in errors and proxy attendance. This paper presents an Attendance Monitoring System Using Multiple Face Recognition for Students, designed to automate attendance recording using computer vision and facial recognition technology. The proposed system detects multiple faces from a single image or video frame and compares the detected faces with previously registered student facial data. Recognized students are identified, and their attendance is automatically recorded in the database. The system is developed using Python, Fast API, and OpenCV-based image processing techniques. The backend provides functionalities for student management, face recognition, attendance recording, session management, and report generation. The proposed system reduces manual effort, saves classroom time, and improves the efficiency of attendance management. The system also provides a centralized approach to maintaining and retrieving attendance records. Further evaluation is required to measure recognition accuracy and performance under different classroom conditions