Title :
Optical attentive associative memory with channel dependent nonlinearity in the weight plane
Author_Institution :
Dept. of Electr. Eng., Connecticut Univ., Storrs, CT, USA
Abstract :
An optical associative processor for two-dimensional image retrieval is described. The system employs variable channel-dependent nonlinearity in the weight plane of the conventional filter-based optical associative memory. Thresholding the filter that is used to store an associative image corresponds to focusing attention on that specific image by altering the strengths of the stored weights in the associative processor. For a severe compression type of nonlinearity, the pixel values of the high spatial frequencies of the filter are increased, which emphasizes the similarity between the input and the selected stored image
Keywords :
computerised picture processing; content-addressable storage; nonlinear optics; optical filters; optical information processing; 2D image retrieval; associative memory; channel-dependent nonlinearity; optical associative processor; optical filters; pixel values; thresholding; weight plane; Associative memory; Computer networks; Concurrent computing; High speed optical techniques; Neural networks; Nonlinear optics; Optical computing; Optical filters; Optical modulation; Signal processing;
Conference_Titel :
Systems, Man and Cybernetics, 1989. Conference Proceedings., IEEE International Conference on
Conference_Location :
Cambridge, MA
DOI :
10.1109/ICSMC.1989.71328
