Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/8176
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
摘要: 
中文字辨識是圖形識別研究領域中的一個重要課題。本文將研究一個適用於中文字辨識的筆劃抽取的方法,結合了非細線化方式以及模糊聚類演算法。主要目的在克服一般細線化演算法在筆劃交叉時產生變形的結果,因而影響筆劃抽取以及辨識的準確率。我們將採用分析文字二值影像的輪廓線及其近似直線轉折點的方法,找出文字骨架線點。最後利用模糊聚類演算法,將平滑化的中文字筆劃以不使用細線化的方式抽取出來。

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.
URI: http://hdl.handle.net/11455/8176
Appears in Collections:電機工程學系所

Show full item record
 
TAIR Related Article

Google ScholarTM

Check


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