| Presentation | 1997/3/19 High-speed,High-accuracy Document Recognition Method using Compressed Character Features and Original Character Features H. KAMADA, K. FUJIMOTO, K. KUROKAWA, H. AKIMOTO, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We prorose a new high-speed,high-accuracy method to recognize text document images.After recognition candidate characters are calculated at high speed using small compressed character features,recognition result are selected using large original character features.For high-speed process,we developed new classification method preserving recognition accuracy,by reflecting original character features distribution in recognition dictionary.For high-accuracy recognition,we developed recognition dictionary using various character patterns generated from fonts.We also developed a new character contour direction features in domains divided as contours points number are same.We realized our proposed method as personal computer software,and verified our method by experimental results. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | document recognition / character features / feature compression / recognition dictionary / character pattern generation.OCR |
| Paper # | PRMU96-205 |
| Date of Issue |
| Conference Information | |
| Committee | PRMU |
|---|---|
| Conference Date | 1997/3/19(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) | High-speed,High-accuracy Document Recognition Method using Compressed Character Features and Original Character Features |
| Sub Title (in English) | |
| Keyword(1) | document recognition |
| Keyword(2) | character features |
| Keyword(3) | feature compression |
| Keyword(4) | recognition dictionary |
| Keyword(5) | character pattern generation.OCR |
| 1st Author's Name | H. KAMADA |
| 1st Author's Affiliation | Fujitsu Laboratories Ltd.() |
| 2nd Author's Name | K. FUJIMOTO |
| 2nd Author's Affiliation | Fujitsu Laboratories Ltd. |
| 3rd Author's Name | K. KUROKAWA |
| 3rd Author's Affiliation | Fujitsu Laboratories Ltd. |
| 4th Author's Name | H. AKIMOTO |
| 4th Author's Affiliation | Fujitsu Laboratories Ltd. |
| Date | 1997/3/19 |
| Paper # | PRMU96-205 |
| Volume (vol) | vol.96 |
| Number (no) | 599 |
| Page | pp.pp.- |
| #Pages | 8 |
| Date of Issue | |