SMART ATTENDANCE USING FACE-RECOGNITION AND AUTOMATED DATABASE MANAGEMENT

Abstract

In traditional educational and corporate environments, manual attendance marking is time- consuming, prone to proxy attendance, and often leads to administrative errors. To address these challenges, this project introduces a Smart Attendance System using Face Recognition. This automated solution leverages computer vision and machine learning to identify individuals and log their presence in real-time. The system utilizes a high-resolution camera to capture facial images, which are then processed using the Haar Cascade algorithm for face detection and Local Binary Patterns Histograms (LBPH) for recognition. Once a face is matched with the database, the system automatically updates an Excel-based or database-driven attendance sheet with the individual's name and timestamp. This eliminates the need for physical registers and ensures high accuracy and integrity in record-keeping. The paper details the system architecture, the integration of Python-based libraries like OpenCV, and the practical implementation in a classroom setting. The proposed system provides a contactless, efficient, and reliable method for attendance management, significantly reducing manual effort and preventing unauthorized presence. The system is uniquely enhanced with a Class Bunk

Report Module that monitors attendance hour-by-hour. If a student is detected in the first hour but missing in subsequent sessions, an automated Email Alert is instantly dispatched to the class teacher via SMTP. This ensures comprehensive accountability, reduces administrative workload, and maintains a secure digital record of student movement.