REAL-TIME OPTOELECTRONIC MORPHOLOGICAL PROCESSOR FOR HUMAN FACE RECOGNITION

Many commercial and law enforcement applications of face recognition n eed to be high-speed and real-time, such as passing through customs qu ickly while ensuring security. However, face recognition by using comp uters only is time-consuming due to the intensive calculation task. Re cently optical implementations of real-time face recognition have attr acted much attention. In this paper, a real-time optoelectronic morpho logical processor for face recognition is presented. it is based on or iginal-complementary composite encoding hit-or-miss transformation, wh ich combines the foreground and background or an image into a whole. O ne liquid-crystal display (LCD) panel is used as two realtime SLMs for both stored images and face images to be recognized, which are of 256 X 256 pixels. A speed or 40 frames/s and four-channel recognition abi lity have been achieved. The experimental results have shown that the processor has an accuracy over 90% and error tolerance to rotation up to 8 deg, to noise disturbance up to 25%, and to image loss up to 40%. (C) 1998 Society of Photo-Optical Instrumentation Engineers. [S0091-3 286(98)00801-0].