ACE: Automated Exam Control and E-Proctoring System Using Deep Face Recognition

With the advent of technology, online exams have become the norm in various government exams such as JEE, NEET, and CET. However., the verification of students during these exams still remains a manual process, leading to potential cases of impersonation and fraud. To address this issue, we propose a system that incorporates automated registration, verification and live proctoring using advanced face recognition and speech technologies. In this paper, we present the integration of existing technologies for an exam management system. The objective of the system is to simplify the registration process, ensure the authenticity of students, and provide live proctoring during exams. Our scope includes designing and implementing the system, evaluating its performance, and suggesting future improvements. The system allows for capturing and storing student details and pictures, cross-verifying pictures during the exam, and live proctoring to monitor the exam environment. Additionally, the system provides an easy-to-use attendance sheet that can be exported to PDF. Our proposed system uses VGG model for face recognition which is a deep learning model that adopts a Convolutional Neural Network (CNN) architecture to acquire knowledge about features from facial images. By extracting features from the images, the model can compare and match them with the existing database pictures, thereby ensuring accurate verification.