Recognition of handwritten numeric characters using neural networks designed on approximate reasoning architecture

Author

Kojima, Yoshihiro ; Yamamoto, Hiroshi ; Kohda, Toshiyuki ; Sakaue, Shigeo ; Maruno, Susumu ; Shimeki, Yasuharu ; Kawakami, Kazutaka ; Mizutani, Mikio

Author_Institution

Intelligent Electron. Lab., Matsushita Electr. Ind. Co. Ltd., Moriguchi, Japan

Volume

3

fYear

1993

fDate

25-29 Oct. 1993

Firstpage

2161

Abstract

We have newly developed a handwritten numeric character recognition system with neural networks based on an approximate reasoning architecture (NARA). Handwritten character recognition is one of the most difficult tasks in an area of pattern recognition because of the variation of handwritten images even in a same category of character. NARA, which consists of a classifier of input data, several sub-neural networks and an integrator of the outputs of sub-neural networks can realize a stable recognition of large variations of handwritten character images, and achieved a correct answer rate of 95.41%, an error rate of 0.20% and a rejection rate of 4.38%.

Keywords

character recognition; image classification; inference mechanisms; neural nets; approximate reasoning architecture; handwritten numeric character recognition; input data classifier; neural networks; Artificial neural networks; Character recognition; Error analysis; Graphics; Handwriting recognition; Instruments; Large-scale systems; Neural networks; Pattern recognition; Writing;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1993. IJCNN '93-Nagoya. Proceedings of 1993 International Joint Conference on

Print_ISBN

0-7803-1421-2

Type

conf

DOI

10.1109/IJCNN.1993.714153

Filename

714153