A neural network based expert system model for conflict resolution

Author

Reddy, N. V Subba ; Nagabhushan, P. ; Gowda, K.C.

Author_Institution

Dept. of Comput. Sci. & Eng., S.J. Coll. of Eng., Mysore, India

fYear

1996

fDate

18-20 Nov 1996

Firstpage

229

Lastpage

232

Abstract

The paper describes a neural network and expert system model for conflict resolution of unconstrained handwritten characters and it completely resolves the confusion between the conflicting characters. The basic recognizer is the neural network. The neural network classifier is a combination of a modified self-organizing map (MSOM) and learning vector quantization (LVQ). It solves most cases, but fails in certain confusing cases. The expert system, the second recognizer, resolves the confusions generated by the neural network. The results obtained from this two-tier architecture are compared with the comments collected from an experiment conducted with a group of human experts specializing in unconstrained handwritten character recognition. The substitution error is eliminated

Keywords

character recognition; expert systems; feature extraction; learning systems; self-organising feature maps; vector quantisation; conflict resolution; conflicting characters; human experts; learning vector quantization; modified self-organizing map; neural network based expert system model; neural network classifier; substitution error; two-tier architecture; unconstrained handwritten character recognition; Artificial neural networks; Character recognition; Computer science; Educational institutions; Expert systems; Feature extraction; Humans; Neural networks; Pattern recognition; Vector quantization;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Information Systems, 1996., Australian and New Zealand Conference on

Conference_Location

Adelaide, SA

Print_ISBN

0-7803-3667-4

Type

conf

DOI

10.1109/ANZIIS.1996.573942

Filename

573942