Real-Time Student Attendance System Using Face Recognition and Cloud Integration

Face recognition has emerged as one of the most impactful image processing applications with significant contributions to authentication systems. This paper presents a robust, real-time attendance system utilizing FaceNet, a deep learning framework, for accurate face recognition. The proposed system employs feature enhancement techniques such as histogram equalization for preprocessing, ensuring reliability under varying lighting conditions. Attendance is marked by detecting and recognizing faces via live webcam feeds, with the data stored securely in a cloud database. Through rigorous testing, the system demonstrated high accuracy and efficiency in diverse scenarios, addressing common challenges like occlusions, pose variations, and environmental changes. Furthermore, the integration of cloud-based storage ensures seamless scalability and accessibility, making the system adaptable to different organizational requirements. The experimental results validate the system's performance under varying environmental conditions, showcasing its ability to meet real-time demands in both educational and professional settings. This work aims to provide a cost-effective, scalable, and user-friendly solution to automate attendance tracking, leveraging cutting-edge facial recognition technology to streamline administrative processes.