• Yash Athwal
• Tejaswini Bhoye
• Dhruv Athwal
• Aayush Kapadi

With the widespread adoption of online education, there arises a need for robust methods to ensure academic integrity during remote assessments. Traditional methods of proctoring such as live proctors or recorded video monitoring are resource-intensive and lack scalability. In response, automated proctoring systems leveraging computer vision techniques have emerged as a promising solution. This paper presents an automated proctoring system that utilizes computer vision algorithms to monitor and detect suspicious behavior during online examinations. The proposed system employs a multi-step process that involves face detection, gaze tracking, posture analysis, and activity recognition to identify potential instances of cheating or misconduct. The face detection module employs convolutional neural networks (CNNs) to detect and track the faces of test-takers throughout the examination session. Gaze tracking algorithms determine where the examinee's eyes are focused, identifying instances of off-screen activity or reference to external materials. Posture analysis algorithms assess the test-taker's body language and posture to detect signs of discomfort or engagement in unauthorized activities. Furthermore, the system utilizes activity recognition techniques to detect anomalous behaviors such as excessive movement or interactions with prohibited objects. By integrating these components into a unified framework, the automated proctoring system can accurately flag instances of potential cheating or academic dishonesty in real-time. Experimental results demonstrate the effectiveness and efficiency of the proposed system in detecting various forms of cheating behavior while minimizing false positives. The system's scalability and adaptability make it suitable for large-scale online assessments across diverse educational settings.

Automated Proctoring, Computer Vision, Online Education, Academic Integrity, Behavior Analysis, Machine Learning, Exam Security.

" Virtual Invigilation System using Computer Vision Techniques", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.h782-h789, April-2024, Available :http://www.jetir.org/papers/JETIR2404790.pdf

" Virtual Invigilation System using Computer Vision Techniques", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. pph782-h789, April-2024, Available at : http://www.jetir.org/papers/JETIR2404790.pdf