Abstract
Binary classification of an object in a two-dimensional image is considered. A spatial light rebroadcaster is shown to be advantageous for learning in this case because it can store the weights and permit upward and downward adjustments. Two learning algorithms, based on the perceptron, are considered. A modification of the perceptron algorithm is developed so that only positive weights are needed. This is convenient because light intensity is positive only. The modified algorithm is shown to converge in a finite number of steps for positive linear separable classes. Optical experiments show the classification of four characters in two groups, in which alternative groupings are used to show robustness. In the second group of experiments the complements of the two-dimensional characters are used, and the convergence is equally fast. Adding the results from the original and complementary patterns provides a discrimination superior to that obtained using either on its own.
© 1993 Optical Society of America
Full Article | PDF ArticleMore Like This
Alastair D. McAulay, Junqing Wang, and Xin Xu
Appl. Opt. 31(26) 5584-5591 (1992)
Alastair D. McAulay, Junqing Wang, and Chen-tai Ma
Appl. Opt. 29(14) 2067-2073 (1990)
John H. Hong, Scott Campbell, and Pochi Yeh
Appl. Opt. 29(20) 3019-3025 (1990)