FaceNet-Based CNN Architecture for Enhanced Attendance Monitoring System

Abstract In the present days, the domain of image classification has seen notable progress, particularly with the rise of Convolutional Neural Networks (CNNs) as a formidable tool in this area. The CNNs excel in detecting intricate patterns and features within images like human eye detection pattern system. The CNN architecture is designed by using convolutional layers, pooling layers, and fully connected layers, enables automatic feature extraction and abstraction, leading to more accurate image classification. By employing machine learning techniques, CNNs continuously improve their ability to classify various images with high precision through training on labelled datasets. In practical scenarios, CNNs find application in image classification for automating attendance tracking of groups. Utilizing facial recognition capabilities, the CNN system accurately identifies and records the attendance of individual persons in real-time, eliminating the necessity of manual tracking. To ensure ease of use, a user-friendly web interface is developed, providing a centralized platform for displaying all attendance records. This integrated solution not only streamlines attendance monitoring but also showcases the seamless integration of advanced image classification techniques and web development, offering an efficient approach to attendance management.