Automated online exam proctoring system using computer vision and hybrid ML classi er

Abstract

The term online proctoring comes hand in hand with online education. There are not many exceptions between traditional education and the online education system except for the fact that online education, as well as online examination, happens over the internet. Due to the Covid-19 situation, when going to schools or colleges and receiving an education is not possible, online education is helping the students to continue their education properly. As much as the importance and necessity of online education can be seen, questions regarding the validity of online exams also emerged. In traditional pen-paper examinations, it is quite di cult for students to cheat under the watchful eyes of the examiner. However, in online examination, the scenario is quite di erent as there is an absence of an invigilator and thus it is quite di cult to observe examinees and detect cheating attempts during online exams. Even though there are already many systems for online proctoring, not all educational institutes can a ord them as the systems are very expensive. In this paper, we have used eye gaze and head pose estimation, along with that voice detection as the main features to design our online proctoring system. Therefore, the purpose of this paper is to use these features to create an online proctoring system using computer vision and machine learning and stop cheating attempts in exams.