跳到主要导航 跳到搜索 跳到主要内容

Word spotting in Chinese document images without layout analysis

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

An approach to searching user-specified words/phrases in Chinese document images, without the requirements of layout analysis, is proposed in this paper. Bounding boxes of Chinese character images are first determined using connected component analysis. Next, a suitable character from the user-specified word/phrase is chosen as the initial character to search for a matching candidate in the document. Once a matched candidate is found, its adjacent characters in the horizontal and vertical directions are examined for matching with other corresponding characters in the user-specified word/phrase, subject to the constraints of positional relation and size similarity. The character matching is done in two stages. The coarse matching is carried out based on the stroke density features. A weighted Hausdorff disiance(WHD) is proposed for the second matching phase. Experimental results show that the proposed method can effectively search the user-specified Chinese word/phrase from horizontal or vertical text lines of document images.

源语言英语
主期刊名Proceedings - 16th International Conference on Pattern Recognition, ICPR 2002
编辑G. Sanniti di Baja, Y. Shirai, M. Kunt, D. Laurendeau, R. Woodham, K. Boyer, L. Shapiro, R. Kasturi, C. Suen, N. Ayache, H. Bunke, H. Christensen
出版商Institute of Electrical and Electronics Engineers Inc.
57-60
页数4
ISBN(电子版)0769516963
DOI
出版状态已出版 - 2002
已对外发布
活动16th International Conference on Pattern Recognition, ICPR 2002 - Quebec City, 加拿大
期限: 11 8月 200215 8月 2002

出版系列

姓名Proceedings - International Conference on Pattern Recognition
3
ISSN(印刷版)1051-4651

会议

会议16th International Conference on Pattern Recognition, ICPR 2002
国家/地区加拿大
Quebec City
时期11/08/0215/08/02

指纹

探究 'Word spotting in Chinese document images without layout analysis' 的科研主题。它们共同构成独一无二的指纹。

引用此