Off-line Character Recognition using On-line Character Writing Information

Authors:
Hiromitsu Nishimura;Takehiko Timikawa
Affiliations:
-;-
Venue:
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Year:
2003

Citing 3
Cited 1

Document Image Decoding Using Markov Source Models

IEEE Transactions on Pattern Analysis and Machine Intelligence
Off-Line Character Recognition Using HMM by Multiple Directional Feature Extraction and Voting with Bagging Algorithm

ICDAR '99 Proceedings of the Fifth International Conference on Document Analysis and Recognition
Substroke Approach to HMM-Based On-line Kanji Handwriting Recognition

ICDAR '01 Proceedings of the Sixth International Conference on Document Analysis and Recognition

Discriminant Substrokes for Online Handwriting Recognition

ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

Recognition of variously deformed character patternsis a salient subject for off-line hand-printed characterrecognition. Sufficient recognition performance forpractical use has not been achieved despite reports ofmany recognition techniques.Our research examines effective recognitiontechniques for deformed characters, extendingconventional recognition techniques using an on-linecharacter writing information containing writing pressuredata. This study extends conventional recognitiontechniques using on-line character writing informationcontaining writing pressure information. A recognitionsystem using simple pattern matching and HMM wasmade for evaluation experiments using Common Hand-printedEnglish character patterns from the ETL6database to determine effectiveness of the proposedextending recognition method. Character recognitionperformance is increased in both expansion recognitionmethods using on-line writing information.