Automated Student Attendance Monitoring and Analytics System for Colleges

Abstract

Attendance management is an essential activity in educational institutions, but traditional methods of recording attendance manually are timeconsuming, prone to human errors, and susceptible to proxy attendance. To overcome these challenges, this project proposes a Face Recognition Based Smart Attendance Management System that automates the attendance process using facial recognition technology. The system is developed using Python, Flask, OpenCV, SQLite, HTML, and CSS, providing a user-friendly web interface for both administrators and users. The administrator can securely log in, upload student face images, and train the face recognition model using the Local Binary Patterns Histograms (LBPH) algorithm. During attendance, the system captures live video through a webcam, detects and recognizes student faces in real time, and automatically records attendance with the corresponding date and time in the SQLite database. This eliminates manual intervention, reduces paperwork, and prevents proxy attendance. The proposed system offers high accuracy, faster attendance processing, secure data management, and improved efficiency compared to conventional attendance methods. It is simple to deploy, costeffective, and suitable for schools, colleges, and other educational institutions. The system demonstrates how computer vision and machine learning techniques can enhance attendance management by providing a reliable, accurate, and automated solution.