Face Recognition For Exam Hall Seating Arrangement Using Deep Learning Algorithm

This research study aims to develop and implement an advanced examination Authentication system using automated face Detection and recognition, leveraging deep learning techniques, to address challenges associated with fraud, impersonation, and inefficiencies in traditional examination processes. The present work has involved two groups. Group1 Refers to the innovative Support Vector Machine (SVM) that is essential for student face identification during exam Verification. Using SVMs to quickly separate visual traits into different classes helps ensure that real student faces are accurately identified. Group 2 This method uses Region Proposal Networks (RPN) and Deep Convolutional Neural Networks (D-CNN) to create customized face Models. Deep learning Model that stops impersonation in the test system by automatically detecting and recognizing faces. Modules for identity Authentication, seating arrangements, hall number Verification, fraud Detection, and attendance monitoring are integrated. The development and implementation of the research represent a significant advancement in the realm of examination security and administration.