A System for Authenticating Student ID Card (SASIC) Using Deep Learning Techniques

Abstract

In educational institutions, using student identification cards for a variety of functions, including identity
verification and access control to campus resources and attendance monitoring, is a standard practice. Enhancing the security and
precision of student identification systems has become more and more important in recent years. As a result, sophisticated
technologies like face recognition and QR code mapping have been incorporated into authentication techniques. The technology
consists of two parts: the first part maps the QR code on the student ID card to a special identification number for the individual
student. To confirm the identification of the student presenting the ID card, the second component uses facial recognition
technology. The system's goal is to reduce the incidence of identity fraud and increase the reliability of student identification
verification. To map the QR code on the student ID card to the appropriate student identity, the suggested method makes use of
deep learning techniques. To determine if a student is wearing an ID card or not, the system also employs a method known as
YOLOV5. Since the system can instantaneously access the student's information by scanning the QR code, it enables quick and
precise identification of pupils. The suggested system includes increased precision in confirming identities of pupils, a decrease in
fraud-related cases, and increased effectiveness in recording attendance and access control. If he or she enters the educational
institution using their separate unique ID card, attendance is tracked on an Excel page and a welcoming chime is sounded. The
technology sounds an alert and delivers an e-mail to the campus administrator with the person's photograph if an unauthorized
person or pupil without an ID tries to get into the institution.