A fast-converging Hamming net used in an offline Chinese character recognition system

Author

Deng, Da ; Yu, Yinglin

Author_Institution

Res. Inst. & Radio & Autom., South China Univ. of Technol., Guangzhou, China

Volume

3

fYear

1992

fDate

7-11 Jun 1992

Firstpage

602

Abstract

The authors (1991) previously proposed a revised version of a holographic memory model based on adaptive feature detection with an attention shift switch. To implement it in a Chinese character recognition system, a fast-converging Hamming net with two memory layers is proposed corresponding to two shiftable stages of feature extraction in the Chinese recognition system. The attention shift process is realized automatically. The system was used to learn 50 Chinese characters. With a recognition test on a set of 30 samples for each character, a recognition rate of about 85% and a recognition speed of about 3.3 words per second were achieved

Keywords

character recognition; feature extraction; holographic storage; neural nets; adaptive feature detection; attention shift process; attention shift switch; fast-converging Hamming net; feature extraction; holographic memory model; offline Chinese character recognition system; Artificial neural networks; Automation; Character recognition; Computer vision; Feature extraction; Optical character recognition software; Optical computing; Optical fiber networks; Optical network units; Switches;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1992. IJCNN., International Joint Conference on

Conference_Location

Baltimore, MD

Print_ISBN

0-7803-0559-0

Type

conf

DOI

10.1109/IJCNN.1992.227108

Filename

227108