Automatic target recognition using a feature-based optical neural networkAn optical neural network based upon the Neocognitron paradigm (K. Fukushima et al. 1983) is introduced. A novel aspect of the architectural design is shift-invariant multichannel Fourier optical correlation within each processing layer. Multilayer processing is achieved by iteratively feeding back the output of the feature correlator to the input spatial light modulator and updating the Fourier filters. By training the neural net with characteristic features extracted from the target images, successful pattern recognition with intra-class fault tolerance and inter-class discrimination is achieved. A detailed system description is provided. Experimental demonstration of a two-layer neural network for space objects discrimination is also presented.
Chao, Tien-Hsin (JPL Pasadena, CA, United States)
August 16, 2013
January 1, 1992
Publication: In: Optical pattern recognition III; Proceedings of the Meeting, Orlando, FL, Apr. 21, 22, 1992 (A93-28672 10-63)