Article’s

Traditional manual attendance methods in educational institutions are time consuming, prone to human error and susceptible to fradualent activities such as proxy attendance. This paper presents an Automated Biometric Attendance System designed to streamline the attendance process using facial recognition technology. The proposed system utilizes a Raspberry pi 4 interfaced with a high – definition USB camera to capture real-time video frames of students entering the classroom. By employing the official Picamera2 library for hardware-optimized capture and Dlib for deep-learning-based feature extraction, the system detects facial landmarks and encodes them into 128-dimensional embeddings. The backend integrates a local SQLite database and a Flask web server to map timestamps to a predefined lecture schedule. This contactless approach eliminates the need for manual name-calling, saving valuable lecture time while ensuring the attendance data is accurate and automatically timestamped. In our testing the system worked accurately in most cases especially in proper lighting conditions, although some challenges were observed in low light. offering a cost effective and secure alternative to RFID or fingerprint-based systems. This project helped us understand practical challenges in real-time face recognition system