RFID and pose invariant face verification based automated classroom attendance system

A compact and reliable classroom attendance system using RFID and face verification is presented in this paper. The RFID system identifies the student using the RFID card and further identity verification of the student is carried out using face recognition technique. RFID uniquely identifies the student based on the card number, then an individual (Fast Adaptive Neural Network Classifier - FANNC) classifier is used to verify the face of each student exclusively. The system is trained and tested by conducting experiments on FEI face database. Each classifier is trained using face images of each student in seven different head poses and it is tested against six different poses. The performance of the system is tested for frontal face verification, head pose varied face verification and detection of proxy attendance is carried out. It is found that the proposed scheme verifies the identity of the student correctly of about 98% for frontal face and two attempts on poses varied face verification. The proxy attendance detection carried out for frontal face resulted in an efficiency of 73.28% and for different poses resulted in an efficiency of 79.29%.