Published Paper Details:

Accurate attendance management remains a persistent challenge in educational settings, where traditional roll-call methods are often inefficient and vulnerable to inaccuracies such as proxy attendance. This research introduces an innovative automated attendance system that utilizes facial recognition technology to enhance the reliability and efficiency of attendance tracking. The proposed system captures images of students at designated intervals during class sessions, thereby minimizing disruption. Utilizing advanced Convolutional Neural Networks (CNNs) for facial recognition, the system identifies students in real time and automatically records their attendance. Each entry is logged with the corresponding subject ID and timestamp, ensuring a comprehensive attendance history. Feature extraction is performed using FaceNet, which effectively maps facial features into a compact representation, while classification is achieved through Support Vector Machines (SVM), allowing for precise identification. This approach not only streamlines the attendance process but also bolsters the security of attendance records by eliminating the potential for fraud. The implementation of this system demonstrates significant improvements in attendance accuracy and operational efficiency, providing educators with a reliable tool to monitor student participation. This research highlights the transformative potential of facial recognition technology in educational administration, paving the way for more innovative solutions in attendance management