[OPTICAL REVIEW Vol. 7, No. 4 (2000) 284-293]
Invariant Pattern Recognition Using Neural Networks Combined with Optical Wavelet Preprocessor
Katsuhisa HIROKAWA,1 Kazuyoshi ITOH2 and Yoshiki ICHIOKA3
1Eastern Hiroshima Prefecture Industrial Research Institute, 3-2-39, Higashifukatsu, Fukuyama, Hiroshima, 721-0974 Japan, 2Department of Applied Physics, 3Department of Material and Life Science, Osaka University, 2-1, Yamadaoka, Suita, Osaka, 565-0871 Japan
(Received December 15, 1999; Accepted March 21, 2000)
A novel pattern-recognition system that is invariant against scale-, position- and rotation-changes is proposed. The system is composed of an array of modular neural networks with local space-invariant interconnections (FELSI) [Appl. Opt. 29 (1990) 4790] and a multiwavelet transform preprocessor. The wavelet decomposition of two-dimensional patterns is optically realized by the VanderLugt correlator. To obtain the multiwavelet transforms simultaneously, we synthesize a correlation filter of multiwavelets using computer-generated holograms. The learning process of the FELSI with the techniques of additional noise and weight decay is shown to contribute to the invariant recognition of the system.
Key words : neural network, wavelet transform, invariant, recognition, optical, additional noise, weight decay