Presentation 2000/3/17
On-line Handwriting Character Recognition based on Pattern Matching Method using On-line Features
Takenori Kawamata, Yuichi Okano, Takashi Hirano, Fumio Yoda,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper describes an on-line handwriting character recognition based on pattern matching method to recognize cursive characters and/or wrong stroke order characters with high accuracy, using robust features extracted by canonical discriminant analysis. Our method uses directional features known as off-line features, cumulative directional features in stroke and the two-dimentional relationship features between strokes as on-line features. We did several experiments to explain the effectiveness of our method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) On-line character recognition / Feature extraction / Pattern matching / Canonical discriminant analysis
Paper # NLC99-81,PRMU99-264
Date of Issue

Conference Information
Committee NLC
Conference Date 2000/3/17(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Natural Language Understanding and Models of Communication (NLC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) On-line Handwriting Character Recognition based on Pattern Matching Method using On-line Features
Sub Title (in English)
Keyword(1) On-line character recognition
Keyword(2) Feature extraction
Keyword(3) Pattern matching
Keyword(4) Canonical discriminant analysis
1st Author's Name Takenori Kawamata
1st Author's Affiliation Information Technology R&D Center, Mitsubishi Electric Corp.()
2nd Author's Name Yuichi Okano
2nd Author's Affiliation Information Technology R&D Center, Mitsubishi Electric Corp.
3rd Author's Name Takashi Hirano
3rd Author's Affiliation Information Technology R&D Center, Mitsubishi Electric Corp.
4th Author's Name Fumio Yoda
4th Author's Affiliation Information Technology R&D Center, Mitsubishi Electric Corp.
Date 2000/3/17
Paper # NLC99-81,PRMU99-264
Volume (vol) vol.99
Number (no) 708
Page pp.pp.-
#Pages 8
Date of Issue