EUVIMEDEUVIMED entdecken
Crossref

AI-Based Online Exam Malpractice Detection System Using MediaPipe, YOLOv8 and OpenCV

K. Varshitha Roy, K. Reena

Research Digest on Engineering Management and Social Innovations · 13.04.2026 · 2 (4)

DOI: 10.46647/icetetas177 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Research Digest on Engineering Management and Social Innovations, online erschienen am 13.04.2026. Verfasst von K. Varshitha Roy und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This project presents an AI-based online exam proctoring system designed to detect malpractice in real time. The system integrates computer vision and deep learning techniques to monitor student behavior during exams. It uses MediaPipe for face and eye tracking to analyze head pose and eye movement, while YOLOv8 is employed for object detection to identify unauthorized items such as mobile phones and electronic devices. OpenCV is used for real-time image processing and frame handling. The system captures video input from the webcam and processes each frame continuously to detect suspicious activities. Eye Aspect Ratio (EAR) is used to detect blinking and eye closure patterns, and head movement analysis helps determine if the user is looking away from the screen. The system also detects excessive eye movement and abnormal behavior patterns. Tab-switching detection is implemented using browser-based APIs to prevent cheating through external resources. Alerts are generated instantly when malpractice is detected. The system provides a user-friendly web interface built using Flask along with HTML, CSS, and JavaScript. Students can log in, select subjects, and take exams under AI monitoring. The application also includes profile management features for personalization. All detection processes occur in near real-time to ensure high accuracy and efficiency. The system minimizes human intervention in online proctoring and enhances exam integrity and fairness. The integration of multiple AI techniques improves reliability and robustness. It reduces the need for manual invigilation and supports continuous monitoring. The architecture is lightweight, scalable, and easy to deploy in educational institutions. Overall, this project demonstrates the practical implementation of artificial intelligence in ensuring secure and trustworthy online examinations.

Zitieren

APA

Roy, K. V., & Reena, K. (2026). AI-Based Online Exam Malpractice Detection System Using MediaPipe, YOLOv8 and OpenCV. Research Digest on Engineering Management and Social Innovations, 2(4). https://doi.org/10.46647/icetetas177

Vancouver

Roy KV, Reena K. AI-Based Online Exam Malpractice Detection System Using MediaPipe, YOLOv8 and OpenCV. Research Digest on Engineering Management and Social Innovations. 2026;2(4). doi:10.46647/icetetas177

BibTeX
@article{Roy2026,
  author = {Roy, K. Varshitha and Reena, K.},
  title = {AI-Based Online Exam Malpractice Detection System Using MediaPipe, YOLOv8 and OpenCV},
  journal = {Research Digest on Engineering Management and Social Innovations},
  year = {2026},
  volume = {2},
  number = {4},
  doi = {10.46647/icetetas177}
}
Kostenlos starten →