Presentation | 2007-03-16 On-Line Recognition of Handwritten Kanji Characters Based on Grammatical Description of Relative Positions between Strokes Ikumi OTA, Ryo YAMAMOTO, Shinji SAKO, Shigeki SAGAYAMA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this paper, we propose a new method for online handwritten Kanji character recognition. In this approach, we turn attention to the hierarchical structure of Kanji which consist of character-parts and strokes, and consider all character patterns to be generated by stochastic context-free grammar (SCFG). As we use both result of stroke recognition and position relationship between character-parts in process of parsing, we can expect that error in stroke and position can be mutually compensated. Furthermore, by expressing position in simple models and share with different Kanji, it enables to make effective results with a few training data, and it becomes possible to recognize untrained Kanji, just by writing down the rules for them. Through our experiment using propsed method, we indicated that the recognition error rate of non-trained Kanji is not inferior to that of trained Kanji, using 1,016 handwritten Kanji written carefully in correct order, which contained in JAIST(Japan Advanced Institute of Science and Technology) online handwritten Kanji database. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Online Handwriting Recognition / Substroke HMM / Spatial Relationship of Subcharacters / Stochastic Context-Free Grammar |
Paper # | PRMU2006-263 |
Date of Issue |
Conference Information | |
Committee | PRMU |
---|---|
Conference Date | 2007/3/9(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 | Pattern Recognition and Media Understanding (PRMU) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | On-Line Recognition of Handwritten Kanji Characters Based on Grammatical Description of Relative Positions between Strokes |
Sub Title (in English) | |
Keyword(1) | Online Handwriting Recognition |
Keyword(2) | Substroke HMM |
Keyword(3) | Spatial Relationship of Subcharacters |
Keyword(4) | Stochastic Context-Free Grammar |
1st Author's Name | Ikumi OTA |
1st Author's Affiliation | Graduate School of Information Science and Technology, The University of Tokyo() |
2nd Author's Name | Ryo YAMAMOTO |
2nd Author's Affiliation | Graduate School of Information Science and Technology, The University of Tokyo |
3rd Author's Name | Shinji SAKO |
3rd Author's Affiliation | Graduate School of Information Science and Technology, The University of Tokyo |
4th Author's Name | Shigeki SAGAYAMA |
4th Author's Affiliation | Graduate School of Information Science and Technology, The University of Tokyo |
Date | 2007-03-16 |
Paper # | PRMU2006-263 |
Volume (vol) | vol.106 |
Number (no) | 606 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |