Please use this identifier to cite or link to this item:
標題: 應用輪廓線分析於中文字筆劃抽取
Stroke Extraction of Chinese Characters Using Contour Analysis
作者: 蔡仲智
關鍵字: character recognition;文字辨識;stroke extraction;non-thinning;fuzzy clustering;筆劃抽取;細線化;模糊聚類
出版社: 電機工程學系

The recognition of Chinese character is an important topic in the research of pattern recognition. In this paper, we will study a hybrid stroke extraction method that combines a non-thinning based approach with the fuzzy clustering algorithm. The main goal of this method is to avoid the artifacts that are generated in traditional thinning algorithm. We will adopt the method of analyzing the contour of the Chinese character of the binary image and the breaking points of the line segments which used to approximate the contour. Then the skeleton points of the character can be found. The representative centers of the stroke segments are initialized by using the skeleton points. Finally, the smooth stroke segments can be obtained via the fuzzy clustering algorithm, and the smooth stroke can be extracted.
Appears in Collections:電機工程學系所

Show full item record
TAIR Related Article

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.