IFRS: An Indexed Face Recognition System Based on Face Recognition and RFID Technologies

Access control systems are in contact with humans in everyday life, it is used in buildings, smartphones, cars, and IoT. Access control systems became an active research area. The performance of an access control system is specified by its speed and accuracy. Biometric systems are powerful access control systems which use humans’ biological or physiological properties to provide access to the restricted data or area. From all of the many biometric system types, the face recognition system is the only type that is delivering the automatic property. Moreover, it is the most acceptable type of biometric systems to the humans. The main challenges in the face recognition system are the degradation of the speed and accuracy when the system database grew bigger. This is because the face recognition system is an identification system that adopts a one to many (1:M) relationship. As a result, there is a need to develop a system with one to one (1:1) relationship, which is a challenging process. Motivated by such challenge, this paper proposes a system called Indexed Face Recognition System (IFRS) which is based on the combination of face recognition technology and Radio Frequency Identification technology. IFRS uses Local Binary Pattern Histogram as a feature vector and Haar-cascade classifier for the face detection. Moreover, the system is enhanced with three pre-processing methods namely: Bilateral filter, Histogram Equalization, and applying Tan and Triggs’ algorithm. In addition, IFRS performs an image normalization processes before and after Face Detection phase to enhance images quality, these process are: Color Conversion and Image Cropping and Resizing. Two experiments were done. The first experiment was done on 400 images with 40 subjects (10 images per subject). The second experiment was done on 210 collected images for 21 subjects (10 images per subject) from University students as a real-life case study. The practical results demonstrates that 4 × 4 image divisions gives better results than 8 × 8 image divisions as far as recognition time, database access time, and storage capacity are concerned. The practical results show that IFRS can reach an accuracy of 100% with a very little amount of time delay that is negligible.