Contextual stochastic model for structural patterns

Author

Chan, Chorkin

Author_Institution

Dept. of Comput. Sci., Hong Kong Univ., Hong Kong

Volume

5

fYear

1998

fDate

11-14 Oct 1998

Firstpage

4207

Abstract

The theory of contextual stochastic modeling of structurally complex and variant patterns like handwritten Chinese characters is presented. The key lies in capturing the contextual information of the strokes in the character image which is segmented into regions systematically. A model for a character captures the region-region and region-pixel stochastic relationship. An unknown image is recognized by computing the pseudo likelihood of identifying its pixels to regions of each model. Based on this theory, an off-line, large vocabulary, hand-written character recognizer has been constructed

Keywords

handwritten character recognition; image segmentation; optical character recognition; stochastic processes; character image segmentation; contextual stochastic model; hand-written Chinese characters; handwritten Chinese characters; off-line large-vocabulary hand-written character recognizer; pixel identification; pseudo likelihood; region-pixel stochastic relationship; region-region stochastic relationship; structural patterns; structurally complex patterns; variant patterns; Computer science; Context modeling; Hidden Markov models; Image generation; Image recognition; Image segmentation; Pixel; Production; Stochastic processes; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man, and Cybernetics, 1998. 1998 IEEE International Conference on

Conference_Location

San Diego, CA

ISSN

1062-922X

Print_ISBN

0-7803-4778-1

Type

conf

DOI

10.1109/ICSMC.1998.727505

Filename

727505