1 October 1999 Optical pattern recognition by extracting least substructuring elements
Author Affiliations +
Optical Engineering, 38(10), (1999). doi:10.1117/1.602221
Abstract
Optical pattern recognition and classification are commonly implemented by means of correlation, and a specialized filter for the patterns to be recognized must be constructed first. Although it has the inherent advantages of high speed, shift invariance, and high distin- guishability, how to build an effective and easily implemented filter or group of filters still remains an open problem. By combining the methods of correlation filtering, transform encoding, and neural network mapping, a least substructuring elements (LSE) extracting method is proposed in this paper. Some basic substructuring elements of a specific group of patterns to be processed could be extracted to compose masks in the least number. Computer simulation upon the 26 English capital letters is provided. One integrated hybrid optoelectronic implementation system is described.
Yue Liu, Shu Chen, Pengyi Guo, Jinyuan Shen, Hongchen Zhai, YanXin Zhang, "Optical pattern recognition by extracting least substructuring elements," Optical Engineering 38(10), (1 October 1999). http://dx.doi.org/10.1117/1.602221
JOURNAL ARTICLE
5 PAGES


SHARE
KEYWORDS
Optical pattern recognition

Optical filters

Optical components

Neural networks

Computer programming

Hough transforms

Image filtering

Back to Top