Automated Proctoring System using Computer Vision Techniques

Maniar, S.; Sukhani, K.; Shah, K.; Dhage, S.

The arrival of COVID-19 has ushered in a new era of distance learning. Since schools and universities have closed, learning has transferred to apps like Google Meet, Microsoft Teams, Zoom, and others. Almost all colleges have changed their curricula to reflect the current reality. Students' practical knowledge deteriorated as a result of the virtual form of learning, and they began attending lectures only for the purpose of attending them. With all of this, their grades and scores should ideally be declining, but the findings came as a shock. It was a fantastic turnaround. Many students outperformed their average score. This is due to the fact that there has never been a way to perform an organized evaluation without using unequal means in the online-mode of education. To address the existing problem, a system that can assist in analysing unfair tactics used by students is required. The employment of proctoring procedures is a big difficulty for the research community when it comes to online examinations. In this paper, we present how to create a complete multi-model system utilising computer vision to prevent the presence of humans throughout the examination. We propose a system that includes a variety of features that students may exploit throughout the test, such as eye gaze tracking, mouth open or close detection, object identification, and head posture estimate using facial landmarks and face detection. Our system can also transform the student's voice into a text format, which might be useful for keeping track of the words said by the student. This might aid the examiner in determining whether or not the student is speaking with someone close. In summary, this research reveals how to prevent cheating in online tests using semi-automated proctoring based on vision and audio capabilities and monitor multiple students at a time. © 2021 IEEE.