Vision-driven Framework For Student Identity Verification Using Face As Hall Ticket In Modern Examination Systems

Abstract

Student Authentication During Examinations Has Emerged As A Critical Challenge In Modern Academic Environments Due To The Rising Incidence Of Impersonation, Identity Fraud, And Unethical Examination Practices. Conventional Verification Methods Such As Hall Tickets, Identity Cards, And Manual Invigilation Are Highly Vulnerable On Document-based Verification And Basic Biometric Techniques Suffer From Poor Scalability, Limited Real-time Effectiveness, And An Inability To Accurately Confirm The Physical Presence Of Candidates, Particularly Under Uncontrolled Examination Conditions. To Address The Limitations Of Traditional Examination Authentication Methods, This Project Proposes A Deep Learning–based Automated Student Authentication System In Which The Student’s Face Acts As A Digital Hall Ticket. The Framework Employs Multi-Task Cascaded Convolutional Neural Networks (MTCNN) For Accurate Facial Detection And Alignment, Enabling Reliable Face Localization Under Varying Pose And Lighting Conditions Commonly Found In Examination Halls. To Ensure That The Candidate Is Physically Present And To Prevent Spoofing Attacks Using Photographs Or Recorded Videos, A CNN-based Liveness Verification Module Is Integrated. After Successful Liveness Validation, FaceNet Is Use Live Facial Inputs With Enrolled Student Data. Upon Authentication, The System Automatically Displays The Student’s Hall Name, Seat Number, Examination Details, And Assigned Invigilator. During The Examination, The Invigilator Captures The Student’s Face, And The System Verifies The Hall Ticket In Real Time. If Impersonation Is Detected, An Instant SMS Alert Is Sent To The Controller Of Examinations And The Respective Head Of Department. Overall, The System Strengthens Examination Security, Prevents Impersonation, And Automates Hall Ticket Verification.

Keywords