A neocognitron synthesized by production rule for handwritten character recognition

Author

Yeung, Daniel S. ; Chan, Hing-Yip ; Lau, Yau Chong

Author_Institution

Dept. of Computing, Hong Kong Polytech., Hung Hom, Hong Kong

fYear

1995

fDate

29-31 May 1995

Firstpage

203

Lastpage

208

Abstract

The objective of this paper is to propose a modified neocognitron with production rules embedded for handwritten character recognition. Structured information about the basic features in a character is stored in the production rules constructed by users. A mapping scheme is used to map these rules into the connection weights of the neocognitron. The ability to represent structured information for characters using production rules provides some insights into how this structured information or knowledge can be processed by the network for its character recognition or refinement in the case where a character is misrecognized. The whole process can be controlled by users by analyzing the results of the recognition by refining the production rules to improve the recognition rate. It is much more flexible, and can be used as tools to build a rapid prototype of a pattern recognizer with fault diagnosis capability

Keywords

character recognition; learning (artificial intelligence); multilayer perceptrons; connection weights; fault diagnosis capability; handwritten character recognition; mapping scheme; neocognitron; pattern recognizer; production rule; rapid prototype; structured information; Character recognition; Embedded computing; Fault diagnosis; Feature extraction; Neural networks; Pattern recognition; Process control; Production systems; Refining; Unsupervised learning;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligence in Neural and Biological Systems, 1995. INBS'95, Proceedings., First International Symposium on

Conference_Location

Herndon, VA

Print_ISBN

0-8186-7116-5

Type

conf

DOI

10.1109/INBS.1995.404260

Filename

404260