| Paper Abstract and Keywords |
| Presentation |
2018-02-16 11:30
A Study of Handwritten Chinese Character Recognition Method Based on Feature Points Extraction Using Micro Scale Space
Masato Suzuki, Daisuke Kitakoshi (Tokyo Kosen) |
| Abstract |
(in Japanese) |
(See Japanese page) |
| (in English) |
Recognition method using local feature extraction is one of the famous strategies to general object recognition. By considering the handwritten chinese characters in the picture as objects, it is possible to apply this algorithm to them. But in character recognition, it is difficult to extract an appropriate local features due to the variety of character shape. In this report, in order to recognize the handwritten chinese characters in such a framework, we set an upper limit on the scale space for extracting characteristic feature points, and try to extract structure information of characters according to the feature extraction form micro scale space. And we also suggest a matching method by dynamically changing the scale of characteristic feature points. In recognition experiments, it is found that we can extract the structure informations from about 80% of characters, and improve the recognition accuracy in comparison with the traditional algorithm regardless of the kind of the reference character pictures. |
| Keyword |
(in Japanese) |
(See Japanese page) |
| (in English) |
Local Feature / Extraction of Character Structure / Micro Scale Space / Handwritten Chinese Character Recognition / / / / |
| Reference Info. |
ITE Tech. Rep. |
| Paper # |
|
| Date of Issue |
|
| ISSN |
|
| Download PDF |
|
| Conference Information |
| Committee |
IEICE-ITS IEICE-IE MMS HI ME AIT |
| Conference Date |
2018-02-15 - 2018-02-16 |
| Place (in Japanese) |
(See Japanese page) |
| Place (in English) |
Hokkaido Univ. |
| Topics (in Japanese) |
(See Japanese page) |
| Topics (in English) |
Image Processing, etc. |
| Paper Information |
| Registration To |
IEICE-IE |
| Conference Code |
2018-02-ITS-IE-MMS-HI-ME-AIT |
| Language |
Japanese |
| Title (in Japanese) |
(See Japanese page) |
| Sub Title (in Japanese) |
(See Japanese page) |
| Title (in English) |
A Study of Handwritten Chinese Character Recognition Method Based on Feature Points Extraction Using Micro Scale Space |
| Sub Title (in English) |
|
| Keyword(1) |
Local Feature |
| Keyword(2) |
Extraction of Character Structure |
| Keyword(3) |
Micro Scale Space |
| Keyword(4) |
Handwritten Chinese Character Recognition |
| Keyword(5) |
|
| Keyword(6) |
|
| Keyword(7) |
|
| Keyword(8) |
|
| 1st Author's Name |
Masato Suzuki |
| 1st Author's Affiliation |
National Institute of Technology, Tokyo College (Tokyo Kosen) |
| 2nd Author's Name |
Daisuke Kitakoshi |
| 2nd Author's Affiliation |
National Institute of Technology, Tokyo College (Tokyo Kosen) |
| 3rd Author's Name |
|
| 3rd Author's Affiliation |
() |
| 4th Author's Name |
|
| 4th Author's Affiliation |
() |
| 5th Author's Name |
|
| 5th Author's Affiliation |
() |
| 6th Author's Name |
|
| 6th Author's Affiliation |
() |
| 7th Author's Name |
|
| 7th Author's Affiliation |
() |
| 8th Author's Name |
|
| 8th Author's Affiliation |
() |
| 9th Author's Name |
|
| 9th Author's Affiliation |
() |
| 10th Author's Name |
|
| 10th Author's Affiliation |
() |
| 11th Author's Name |
|
| 11th Author's Affiliation |
() |
| 12th Author's Name |
|
| 12th Author's Affiliation |
() |
| 13th Author's Name |
|
| 13th Author's Affiliation |
() |
| 14th Author's Name |
|
| 14th Author's Affiliation |
() |
| 15th Author's Name |
|
| 15th Author's Affiliation |
() |
| 16th Author's Name |
|
| 16th Author's Affiliation |
() |
| 17th Author's Name |
|
| 17th Author's Affiliation |
() |
| 18th Author's Name |
|
| 18th Author's Affiliation |
() |
| 19th Author's Name |
|
| 19th Author's Affiliation |
() |
| 20th Author's Name |
|
| 20th Author's Affiliation |
() |
| Speaker |
Author-1 |
| Date Time |
2018-02-16 11:30:00 |
| Presentation Time |
15 minutes |
| Registration for |
IEICE-IE |
| Paper # |
|
| Volume (vol) |
vol.42 |
| Number (no) |
|
| Page |
|
| #Pages |
|
| Date of Issue |
|