Machine Learning-Based Face Detection and Recognition System for Online Examination Monitoring

Abstract

The rapid growth of online education has created a strong need for secure and reliable online examination systems that can effectively monitor students and prevent malpractice. This project proposes a machine learning-based face detection and recognition system designed for monitoring students during online examinations using webcam-based image processing techniques. The system captures and analyzes students’ facial activities in real time to verify identity and detect suspicious behavior during examinations. Facial features are extracted using the Eigenface algorithm, which converts facial images into feature vectors for efficient recognition, while the Support Vector Machine (SVM) algorithm is used for accurate face classification and detection. The proposed method addresses common challenges in face recognition such as lighting variations, facial expressions, image noise, pose changes, and scaling issues that reduce recognition accuracy. By combining Eigenface feature extraction with SVM classification, the system achieves faster and more reliable face recognition suitable for online exam monitoring. The developed system enhances student authentication, improves examination security, and minimizes malpractice in virtual learning environments. Experimental analysis shows that the proposed approach provides improved accuracy and computational efficiency compared to traditional face recognition methods, making it an effective and intelligent solution for secure online examination monitoring in educational institutions.