Title :
Robust identification of human face using mosaic pattern and BPN
Author_Institution :
NTT Human Interface Lab., Kanagawaken, Japan
fDate :
31 Aug-2 Sep 1992
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
Keywords :
backpropagation; neural nets; pattern recognition; BPN; backpropagation network; defocused images; human face recognition; mosaic pattern; noisy images; personal identification; Face recognition; Feature extraction; Humans; Image edge detection; Image recognition; Laboratories; Neodymium; Neural networks; Robustness; Statistical analysis;
Conference_Titel :
Neural Networks for Signal Processing [1992] II., Proceedings of the 1992 IEEE-SP Workshop
Conference_Location :
Helsingoer
Print_ISBN :
0-7803-0557-4
DOI :
10.1109/NNSP.1992.253683