| 大会名称 |
|---|
| 2009年 情報科学技術フォーラム(FIT) |
| 大会コ－ド |
| F |
| 開催年 |
| 2009 |
| 発行日 |
| 2009/8/20 |
| セッション番号 |
| 7H |
| セッション名 |
| 文字認識 |
| 講演日 |
| 2009/09/04 |
| 講演場所(会議室等) |
| H会場（9号館2F 923教室） |
| 講演番号 |
| H-014 |
| タイトル |
| A Development of Pattern-based Online Handwriting Uyghur Character Recognition System |
| 著者名 |
| Zaydun Yidayet, Saitoh Tsuyoshi, |
| キーワード |
| Online Character Recognition, Uyghur Character Recognition, Pattern-based Recognition |
| 抄録 |
|
This paper describes the experiment results of pattern-based online Uyghur character recognition. For the purpose of classification of the sub-word patterns, samples containing 4 million characters were collected and analyzed. As the result of the analysis, we found that a pattern-based recognition approach was applicable effectively, because average recognition rate on the 12 volunteers’ data became 91% for one-character sub-words and 87% for two-character sub-words. We also discuss that a better recognition rate will be obtain by improving the standard pattern database for our system. |
| 本文pdf |
| PDF download (159.9KB) |