Automated Proctoring System using Machine Learning

The rapid growth of online education has necessitated the need for effective proctoring systems to maintain academic integrity and ensure fair examinations. Traditional methods of proctoring, such as in-person invigilation, are not feasible for online exams. To address this challenge, an Automated Proctoring System using Computer Vision Techniques is proposed. This system employs advanced computer vision algorithms to monitor and analyze the behavior of candidates during online examinations.The Automated Proctoring System utilizes a webcam and microphone to monitor the test environment in real-time. Computer vision techniques are employed to detect and track the examinee’s face, gaze direction, eye movements, body posture, and suspicious activities. Machine learning models are trained to identify abnormal patterns of behavior, such as looking away from the screen frequently or having multiple faces in the camera frame. These detected anomalies trigger alerts to the examiners for further investigation.The proposed system aims to enhance exam security by mitigating academic dishonesty, including cheating, impersonation, and unauthorized aids. By leveraging computer vision, it provides a non-intrusive and scalable solution for monitoring online exams. Furthermore, this system respects privacy and adheres to ethical considerations, ensuring data protection and minimizing false positives.