计算机工程与应用 ›› 2010, Vol. 46 ›› Issue (9): 180-182.DOI: 10.3778/j.issn.1002-8331.2010.09.051

• 图形、图像、模式识别 • 上一篇    下一篇

笔迹图像中的单个汉字字符分割

于 明,张彦云,薛翠红,孙林娟   

  1. 河北工业大学 计算机科学与软件学院,天津 300401
  • 收稿日期:2008-09-19 修回日期:2008-12-15 出版日期:2010-03-21 发布日期:2010-03-21
  • 通讯作者: 于 明

Image segmentation algorithm of single handwritten Chinese characters

YU Ming,ZHANG Yan-yun,XUE Cui-hong,SUN Lin-juan   

  1. School of Computer Science and Engineering,Hebei University of Technology,Tianjin 300401,China
  • Received:2008-09-19 Revised:2008-12-15 Online:2010-03-21 Published:2010-03-21
  • Contact: YU Ming

摘要: 提出了一套完整的针对单字的笔迹图像分割算法,选用不同的笔迹样本作了验证实验,对实现单字分割做了全面的阐述论证。将模板分割算法中的行分割、字分割、单字图像库建立和基于模板匹配的分割算法结合在一起,提高了算法的运算速度和精确度。利用50幅笔迹样本进行测试,92%的单字分割样本可以作为单字模板,应用模板匹配分割算法92%的样本可以实现单字提取。

关键词: 分割算法, 行分割, 字分割, 单字图像库, 模板匹配分割

Abstract: A set of complete handwriting image segmentation algorithm according to single character is proposed.Different samples are used to do proving experiments,and the realization of character segmentation is described comprehensively.This paper combines the line segmentation,character segmentation,image database of single character of the template segmentation and the segmentation algorithm based on the template matching segmentation,and improves the speed and accuracy of algorithm.The algorithm is validated with 50 handwriting samples.92% of the single character of the segmentation samples can be used as the single character template.The application of template matching segmentation single character can be extracted in 92% of the samples.

Key words: segmentation algorithm, line segmentation, character segmentation, image database of single character, template matching segmentation

中图分类号: