A reliability improvement of NN based OCR using rules and committee classifiers

Author

Radevski, Vladimir ; Bennani, Younes ; Cakmakov, Dusan

Author_Institution

CNRS, Univ. de Paris-Nord, Villetaneuse, France

fYear

2000

fDate

16-16 June 2000

Firstpage

177

Lastpage

182

Abstract

The ability of Neural Networks (NN) to learn from training samples in order to generate desired decision regions, has been widely used in recent pattern recognition applications. In this paper, the cooperation of two feature families through a committee of NN based classifiers is investigated. The cooperation scheme is based on two stage classification using a combination of rule-based and statistical approaches. The corresponding results that show the significant improvement of the system reliability are also presented.

Keywords

feature extraction; knowledge based systems; learning by example; neural nets; optical character recognition; committee classifiers; decision regions; learning from training samples; neural net based OCR; reliability improvement; rules; statistical approaches; two stage classification; Character recognition; Data mining; Electronic mail; Feature extraction; Handwriting recognition; Neural networks; Optical character recognition software; Pattern recognition; Pixel; Reliability;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Technology Interfaces, 2000. ITI 2000. Proceedings of the 22nd International Conference on

Conference_Location

Pula, Croatia

ISSN

1330-1012

Print_ISBN

953-96769-1-6

Type

conf

Filename

915897