Cheating Detection in Examinations Using Improved YOLOv8 with Attention Mechanism

Abstract

Examinations are among the most widely used and effective methods for assessing knowledge mastery, both domestically and internationally, and are extensively used in various talent-selection processes. Currently, offline exam venues usually rely on on-site manual invigilation combined with exam-monitoring videos to further strengthen invigilation efforts. However, this invigilation method not only utilizes large amounts of human and material costs but also cannot comprehensively detect cheating behavior during exam processes and thus fairness cannot be guaranteed. To improve the efficiency of video reviews during invigilation, save labor costs, and strengthen invigilation efforts, this study proposes the use of target detection algorithms to achieve automatic detection of cheating actions in the exam room. To improve the speed of video detection, a student's abnormal-behavior detection method was proposed based on improved YOLOv8 and attention mechanism to achieve real-time detection of cheating actions in an exam room on a regular performance computer. The results showed that the detection accuracy of the improved YOLOv8 model reached 82.71%, thus meeting the application requirements.