| 講演抄録/キーワード |
| 講演名 |
2011-03-10 10:00
A Text Search Method based on Directional Feature Matching ○Pasitthideth Luangvilay・Bilan Zhu・Masaki Nakagawa(Tokyo Univ. of Agr and Tech.) PRMU2010-239 |
| 抄録 |
(和) |
(まだ登録されていません) |
| (英) |
In this paper, we describe a method of retrieving online handwritten text by directional feature matching. Although text search into the character recognition candidate lattice has been elaborated, the character recognition based approach does not support languages which are not assumed. The proposed method is liberated from this constraint. It first hypothetically segments online handwritten text into character pattern blocks and then extracts directional features from object text patterns generated by combining the character pattern blocks. Then, the dimensionalities of those features are further reduced by Fisher linear discriminate analysis (FDA) and those results are employed to measure the similarity between the object text patterns and a query pattern by block-shift matching. This paper discusses the retrieval performance in comparison with a character recognition based method. |
| キーワード |
(和) |
/ / / / / / / |
| (英) |
text search / online handwritten text / digital ink / directional feature matching / / / / |
| 文献情報 |
信学技報, vol. 110, no. 467, PRMU2010-239, pp. 13-17, 2011年3月. |
| 資料番号 |
PRMU2010-239 |
| 発行日 |
2011-03-03 (PRMU) |
| ISSN |
Print edition: ISSN 0913-5685 Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
| PDFダウンロード |
PRMU2010-239 |