Convolutional Neural Network based Virtual Exam Controller
Kavish Garg, Kunal Verma, Kunal Patidar, Nitesh Kumar Tejra, Kunal Patidar
Abstract
In today's IT World, online examination has become very popular. It substituted all of the Offline Test inconveniences. But there is still a big question about the security of online examination. In this system camera at the client computer is used to track the student's face during the exam, and can be used to monitor the behavior of test person and to stop any malicious practices. The system will track(detect), tag, and identify the students face using Haar Cascade Classifier and deep learning and apply some constraints to stop these practices(e.g. Multiple face detection). Our system will play a key role in securing online exams and can be a role model to already existing online exam procurement systems which are faulty and too much forgiving.The system developed can be used in a course as part of a randomized Multiple-Choice test as well as can be integrated with online learning programs to monitor the behavior of the students for their better results which however will need further advancements.