Proct-Xam - AI Based Proctoring

ABSTRACT

The COVID-19 pandemic has dramatically changed the education sector, which led to a rise in online learning. E-learning has exponentially increased and it has become difficult to conduct exams offline too. Need for online education and conducting online exams has led various institutes and educational sectors to develop a platform where exams can be proctored. The ability to proctor online examinations more effectively has become a crucial factor in the education sector. Presently, human proctoring is the most common approach of evaluation, by monitoring them during exams via a webcam. It has become challenging for supervisors/teachers to examine and conduct online exams. In addition to that, studies say that there has been a significant rise in cheating during online exams. The main objective of the project is to conduct honest, faithful examination by developing an AI based online proctoring system which will help teachers to check the examinee's authenticity, eliminate suspicious behaviour during the exam and keep track of students throughout the exam time. In addition to that, conducting smooth and honest examinations will increase everyone's trust in the online education sector. Proposed project is a website developed using AI algorithms such as CNN/RNN algorithm which monitors students during the exam, allowing students to attend the exam from any location, which will help in detecting any malicious activities via webcam and guarantee fair evaluation of exams. Vision based tracking consists of Eye ball tracking, Lip movement, additional member detection in frame and more. The website will also ensure that the candidate is sharing his/her screen. Conclusion, the proposed project provides an online platform with features like view students screen anytime, send warning messages, terminate someone's exam, eye tracker, lip tracker for conducting effective exams. © 2022 IEEE.