Automated Online Exam Proctoring System Using Computer Vision Hybrid ML Classifier

This paper proposes an AI-driven online exam proctoring system designed to uphold academic integrity through a Hybrid Machine Learning Classifier. The system incorporates facial recognition, head pose estimation, eye tracking, object detection, and person identification to enable real-time monitoring of examinations. With a 95 percentage accuracy rate and minimal false positives, it ensures a secure and fair testing environment. The system supports various exam formats, including objective, subjective, and practical assessments, making it highly adaptable. Ethical considerations are addressed through strong privacy safeguards, data encryption, and compliance with security protocols. Additionally, it minimizes human intervention, reduces operational costs, and enhances accessibility for remote learners. This solution establishes a reliable framework for secure, automated, and scalable online assessments in education and corporate training.