摘要:
Today, face recognition algorithms are generally realized in software. However, such algorithms have low execution efficiency and suffer from not being robust enough to withstand hacking. Face recognition technology implemented in hardware can overcome these weaknesses. Additionally, hardware-based face recognition as a security system offers high reliability, imperviousness to hacking, and high-execution speed. Thus, hardware-based security system can be deployed safely in applications that need high reliability and speed. Given today’s advances in Field Programmable Gate Array (FPGA) technology, face recognition technology quite efficiently can be implemented. One of the main challenges in face recognition system is finding informative and discriminative information about each subject. Although algorithms have been tested and compared extensively with each to involve the hardware implementation of the best technique by using FPGA technologies, there has been remarkably little work comparing the accuracy of computer-based face recognition systems. We compared eight state-of-the-art face recognition algorithms with three different databases: (i) faces94; (ii) Olivetti research lab (ORL), and (iii) Indian face database (IFD).
展开