| Presentation | 2020-02-27 Location estimation algorithm of letter in historical document by using word spotting Rei Nagaya, Masato Suzuki, Daisuke Kitakoshi, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | At present, digitalization of historical documents is carried out to preserve the degraded documents. Digitalization work has been stagnated due to lack of experts; therefore, the traditional OCR technology has been also used. However, all characters of historical documents had to be separated manually or semi-automatically, since it is difficult to automatically separate the connected characters in cursive style. In this paper, we propose a method to reduce the time and effort for making historical documents into text by performing character segmentation and recognition processing simultaneously using Word Spotting. In this method, position and character type are determined from the result of Word Spotting for each character type of Hiragana, and these areas are excluded in the next processing. And, the processing is carried out sequentially according to the priority determined by frequency of appearance and accuracy of each character type. As a result, it is possible to detect the character areas for each character type in a few minutes by specifying several areas of this character in the document. In the experiments on a proposed algorithm, 30 to 40% of characters in some documents can be detected correctly. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Historical Document Recognition / Word Spotting / DTW / Cursive Style |
| Paper # | ITS2019-39,IE2019-77 |
| Date of Issue | 2020-02-20 (ITS, IE) |
| Conference Information | |
| Committee | ITE-HI / IE / ITS / ITE-MMS / ITE-ME / ITE-AIT |
|---|---|
| Conference Date | 2020/2/27(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Hokkaido Univ. |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Image Processing, etc. |
| Chair | Takehiro Nagai(Tokyo Inst. of Tech.) / / / Norihiko Ishii(NHK) / Norio Tagawa(Tokyo Metropolitan Univ.) / Nobuhiko Mukai(Tokyo Cisy Univ.) |
| Vice Chair | / / / / Hiroyuki Arai(Nippon Institute of Technology) / Hisaki Nate(Tokyo Polytechnic Univ.) |
| Secretary | (NTT) / / / (Fukuoka Univ.) / Hiroyuki Arai(NHK) / Hisaki Nate(NHK) |
| Assistant | |
| Paper Information | |
| Registration To | Technical Group on Human Inormation / Technical Committee on Image Engineering / Technical Committee on Intelligent Transport Systems Technology / Technical Group on Multi-media Storage / Technical Group on Media Engineering / Technical Group on Artistic Image Technology |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Location estimation algorithm of letter in historical document by using word spotting |
| Sub Title (in English) | |
| Keyword(1) | Historical Document Recognition |
| Keyword(2) | Word Spotting |
| Keyword(3) | DTW |
| Keyword(4) | Cursive Style |
| 1st Author's Name | Rei Nagaya |
| 1st Author's Affiliation | National Institute of Technology, Tokyo College(NITTC) |
| 2nd Author's Name | Masato Suzuki |
| 2nd Author's Affiliation | National Institute of Technology, Tokyo College(NITTC) |
| 3rd Author's Name | Daisuke Kitakoshi |
| 3rd Author's Affiliation | National Institute of Technology, Tokyo College(NITTC) |
| Date | 2020-02-27 |
| Paper # | ITS2019-39,IE2019-77 |
| Volume (vol) | vol.119 |
| Number (no) | ITS-421,IE-422 |
| Page | pp.pp.207-212(ITS), pp.207-212(IE), |
| #Pages | 6 |
| Date of Issue | 2020-02-20 (ITS, IE) |