| Presentation | 2008-02-22 Online Handwritten Kanji String Recognition Based on Grammar Description of Character Structures Ikumi OTA, Ryo YAMAMOTO, Takuya NISHIMOTO, Shigeki SAGAYAMA, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this paper, we discuss a method for online handwritten Kanji character recognition by describing the structure of Kanji using Context-Free Grammar (CFG), and extend it in order to recognize Kanji character strings. 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 from stochastic context-free grammar (SCFG). As we use both likelihoods of strokes and position relationship between character-parts in the process of parsing, it is expected that likelihoods of strokes and positions jointly improved the likelihood accuracy. Using this method on Kanji strings enables the system to deal with both of the main problems together, namely, the decision of boundaries between letters and isolated Kanji character recognition process. Therefore the recognition error due to the failure of letter boundary decision can be compensated. We evaluated the method using handwritten phrases consist of 2 or 3 Kanji characters contained in JAIST Online Handwriting Database, and gained the recognition rate of 90.80% without using language models. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Online Handwriting Recognition / Character String Recognition / Substroke HMM / Spatial Relationship of Subcharacters / Stochastic Context-Free Grammar |
| Paper # | PRMU2007-227 |
| Date of Issue |
| Conference Information | |
| Committee | PRMU |
|---|---|
| Conference Date | 2008/2/14(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) | Online Handwritten Kanji String Recognition Based on Grammar Description of Character Structures |
| Sub Title (in English) | |
| Keyword(1) | Online Handwriting Recognition |
| Keyword(2) | Character String Recognition |
| Keyword(3) | Substroke HMM |
| Keyword(4) | Spatial Relationship of Subcharacters |
| Keyword(5) | 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 | Takuya NISHIMOTO |
| 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 | 2008-02-22 |
| Paper # | PRMU2007-227 |
| Volume (vol) | vol.107 |
| Number (no) | 491 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |