Offline character recognition using online character writing information

Author

NISHIMURA, Hiromitsu ; TIMIKAWA, Takehiko

Author_Institution

Dept. of Inf. & Comput. Sci., Kanagawa Inst. of Technol., Japan

fYear

2003

fDate

3-6 Aug. 2003

Firstpage

168

Abstract

Recognition of variously deformed character patterns is a salient subject for offline hand-printed character recognition. Sufficient recognition performance for practical use has not been achieved despite reports of many recognition techniques. Our research examines effective recognition techniques for deformed characters, extending conventional recognition techniques using online character writing information containing writing pressure data. This study extends conventional recognition techniques using online character writing information containing writing pressure information. A recognition system using simple pattern matching and HMM was made for evaluation experiments using common hand-printed English character patterns from the ETL6 database to determine effectiveness of the proposed extending recognition method. Character recognition performance is increased in both expansion recognition methods using online writing information.

Keywords

document image processing; handwritten character recognition; hidden Markov models; image matching; ETL6 database; HMM; common hand-printed English character pattern; deformed character; hand-printed character recognition; hidden Markov model; image-weighting filter; offline character recognition; online character writing information; pattern matching; writing pressure data; writing pressure information; Character recognition; Computer vision; Data mining; Databases; Hidden Markov models; Layout; Neural networks; Pattern matching; Pattern recognition; Writing;

fLanguage

English

Publisher

ieee

Conference_Titel

Document Analysis and Recognition, 2003. Proceedings. Seventh International Conference on

Print_ISBN

0-7695-1960-1

Type

conf

DOI

10.1109/ICDAR.2003.1227653

Filename

1227653