Abstract
The backpropagation network (BPN) is applied to human face recognition. A mosaic pattern transformed from the central part of a human face image is put into the BPN for personal identification. This combination succeeds in recognition of hundreds of people with robustness not only for defocused or noisy images but also for images of different face expressions or different ages. Hidden units of the BPN extract peculiar and delicate features of the face, which cannot be obtained from existing statistical methods. A few hidden units can especially select only men or women. Moreover, a BPN with an additional unit for processing unfamiliar faces is proposed.

This publication has 4 references indexed in Scilit: