Key points are not available for this paper at this time.
This paper presents an intelligent proctoring system designed to enhance the integrity of examination environments using computer vision technologies. The system integrates motion detection and face recognition algorithms to identify and record suspicious activities in real-time. Built on a Raspberry Pi 4B platform with a USB camera, the system continuously monitors the exam hall, detecting behaviors such as unauthorized movements, excessive head gestures, and student interactions that may indicate cheating. Upon detection of such activities, the system generates alerts for invigilators and securely stores visual evidence for post-exam review. The implementation leverages OpenCV for video processing and behavior analysis, achieving an overall detection accuracy of 91.5% across 100 exam sessions. The proposed solution demonstrates a cost-effective, scalable, and automated approach to proctoring, reducing reliance on manual supervision and offering enhanced security for both physical and potentially remote exam settings.
Mohapatra et al. (Fri,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: