Attendance Management Using Face Recognition

Traditional attendance methods are time-consuming, prone to human error, and often lack reliability. To address this, we propose an intelligent Attendance Management System that integrates computer vision, machine learning, and web-based automation to mark student attendance efficiently and accurately. The system captures either a 3-second classroom video or a single photo, which is then processed to recognize student faces and automatically mark their attendance in an Excel sheet. Initially, the system is trained using individual student images or videos to identify them accurately. The solution is built using Streamlit for the web interface, OpenCV for image/video processing, and Python-based logic for recognition and automation. Unlike traditional biometric or manual methods, our system supports both image and video input for training and real-time attendance marking. This lightweight, cost-effective, AI-driven system significantly reduces manual effort and ensures accurate record-keeping, thus enhancing institutional efficiency.