File Download
There are no files associated with this item.
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: DISTORTION MODEL FOR CHINESE CHARACTER GENERATION.
| Title | DISTORTION MODEL FOR CHINESE CHARACTER GENERATION. |
|---|---|
| Authors | |
| Issue Date | 1985 |
| Abstract | A distortion model is proposed to expand a given database so that it represents more variations in handwriting than the original. The model performs appropriate shearing and warping operations on the sample characters in order to generate additional samples with variations in stroke directions and in the relative sizes between different subpatterns of the character. It is found that recognition systems trained up with such additional samples perform much better than those without using such samples. This shows that the proposed model is practically useful. |
| Persistent Identifier | http://hdl.handle.net/10722/157997 |
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.author | Leung, CH | en_US |
| dc.contributor.author | Cheung, YS | en_US |
| dc.contributor.author | Chan, KP | en_US |
| dc.date.accessioned | 2012-08-08T08:57:38Z | - |
| dc.date.available | 2012-08-08T08:57:38Z | - |
| dc.date.issued | 1985 | en_US |
| dc.identifier.uri | http://hdl.handle.net/10722/157997 | - |
| dc.description.abstract | A distortion model is proposed to expand a given database so that it represents more variations in handwriting than the original. The model performs appropriate shearing and warping operations on the sample characters in order to generate additional samples with variations in stroke directions and in the relative sizes between different subpatterns of the character. It is found that recognition systems trained up with such additional samples perform much better than those without using such samples. This shows that the proposed model is practically useful. | en_US |
| dc.language | eng | en_US |
| dc.title | DISTORTION MODEL FOR CHINESE CHARACTER GENERATION. | en_US |
| dc.type | Conference_Paper | en_US |
| dc.description.nature | link_to_subscribed_fulltext | en_US |
| dc.identifier.scopus | eid_2-s2.0-0022287099 | en_US |