北京大学学报(自然科学版) ›› 2016, Vol. 52 ›› Issue (1): 81-88.DOI: 10.13209/j.0479-8023.2016.016

上一篇    下一篇

一种基于三维空间信息的字形匹配方法

刘颖滨, 孙燕南, 荀恩东   

  1. 北京语言大学大数据与语言教育研究所, 北京 100083
  • 收稿日期:2015-06-03 出版日期:2016-01-20 发布日期:2016-01-20
  • 通讯作者: 刘颖滨, E-mail: liuyb(at)blcu.edu.cn
  • 基金资助:
    国家自然科学基金(61170162, 61202249)和国家语言文字工作委员会科研项目(YB125-42)资助

Chinese Calligraphy Alignment Based on 3D Point Set Registration

LIU Yingbin, SUN Yannan, XUN Endong   

  1. Institute of Big Data and Language Education, Beijing Language and Culture University, Beijing 100083
  • Received:2015-06-03 Online:2016-01-20 Published:2016-01-20
  • Contact: LIU Yingbin, E-mail: liuyb(at)blcu.edu.cn

摘要:

提出一种基于三维空间信息的字形匹配方法。首先将字形轮廓Bézier 曲线的二维控制点集扩展至三维, 然后为三维点集建立高斯混合模型, 最后通过最小化高斯混合模型间的欧氏距离(L2)完成匹配。采用三维空间信息可以充分利用字形所蕴含的内在约束条件。采用高斯混合模型有利于在匹配过程中保持字形整体结构特征和局部书写特征。实验结果表明, 该方法提升了汉字单笔画以及整字字形匹配的准确度和美观度, 并且具有稳定性高、扩展性强的特点。

关键词: 字形匹配, 高斯混合模型, 点集匹配, 三维空间

Abstract:

This paper presents an innovative method to align two glyph contours with three steps. First, 2D Bézier curve control points of glyph contours of each character are expanded into 3D space. Second, a Gaussian Mixture Model (GMM) is constructed using this 3D point set. Finally, the authors establish alignment by minimizing the Euclidean Distance (L2) between two GMMs and then apply transformation accordingly. Expansion to 3D space helps make use of inherent constraints of Chinese calligraphy beyond 2D coordinates. The advantage of using Gaussian Mixture Model is to maintain both the overall shape property and the local writing features during the alignment process. Experiments results verify the feasibility and effectiveness of proposed method and it performs well for both single stroke and whole character.

Key words: Chinese calligraphy alignment, Gaussian Mixture Model, point set registration, 3D point set

中图分类号: