Signals & Systems Imaging Real-time Facial Recognition using VLSI

When joint with a web cam, digitizer of image, & VLSI picture correlate chip, an IBM PC can be utilized for real-time facial identification. A semi-controlled lighting environment is used to capture a single frontal facial image, which is then preprocessed and template extracted before being correlated with a database of 173 photographs and finally post processed to yield identification. These steps use a single frontal facial image. Software development, VLSI hardware, picture preprocessing, and facial recognition are explored. The completely VLSI image corrugator can execute 340 Mop/second and increase 20 speed compared to adjusted assembly program execution on an 80486/66DX2. The algorithm recognizes a user from 173 photos of 34 persons in two to three seconds. Cross-authentication on the abstemiously variable databank yields a conservative 88% recognition rate for the system.