OPTICAL NEURAL-NETWORK USING VECTOR-FEATURE EXTRACTION

an optical neural network model and a key device for its optical imple mentation are proposed, The model, named the vector-feature-extracting optical neural network, can correctly recognize hand-written letters and can easily be implemented in optics. The key device, named a featu re-extracting optical neuron device, can selectively extract specific line segments included in an optical input pattern. In this paper the structure and recognition process of the vector-feature-extracting opt ical neural network are shown in detail. The function, of the feature- extracting optical neuron device is experimentally shown. In addition, the optical system based on the vector-feature-extracting optical neu ral network is described.