基于骨架图匹配的汉字变形技术

刘敏; 詹华年; 梁晓辉; 胡佳佳

doi:10.13700/j.bh.1001-5965.2014.0469

基于骨架图匹配的汉字变形技术

doi: 10.13700/j.bh.1001-5965.2014.0469

1.
北京航空航天大学计算机学院, 北京 100191
2. 北京师范大学文学院, 北京 100875

基金项目: 国家自然科学基金资助项目(61170186); 国家科技支撑计划资助项目(2014BAK18B01)

详细信息

作者简介:
刘敏(1988—), 男, 安徽无为人, 硕士生, lium@buaa.edu.cn

通讯作者:
梁晓辉(1970—), 男, 教授, 山西吕梁人, lxh@vrlab.buaa.edu.cn, 主要研究方向为计算机图形学、虚拟现实.

中图分类号: TP37
计量
- 文章访问数: 1291
- HTML全文浏览量: 119
- PDF下载量: 39156
- 被引次数: 0
出版历程
- 收稿日期: 2014-04-28
- 网络出版日期: 2015-02-20

Morphing technology for Chinese characters based on skeleton graph matching

1.
School of Computer Science and Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100191, China
2. School of Chinese Language and Literature, Beijing Normal University, Beijing 100875, China

摘要

摘要: 不同时代的汉字变化较大,自动产生它们之间的变形动画是一个具有挑战性的任务.为此尝试使用一个新方法解决该问题.首先将源汉字和目标汉字分割成对应的部件,然后根据部件的骨架和特征点将其分解为笔画并建立图模型,用笔画路径的相似度进行图模型的匹配来产生对应关系.最后根据匹配的结果为源汉字和目标汉字的轮廓建立同构三角形,并计算插值产生动画.实验当中将新方法的汉字匹配的效果与现有方法进行对比,并展示了所产生的变形动画,结果表明本文所提出的方法可以产生不同时代的汉字间的对应关系,并能生成平滑的变形动画.
- 汉字 /
- 对应 /
- 图模型匹配 /
- 形状插值 /
- 变形动画
Abstract: Automatically shape morphing for Chinese characters represented in different writing stages is a challenging task. A novel method was proposed to solve this problem. Specifically, the source and target Chinese characters were decomposed to corresponding components. And then, the components were decomposed to strokes which were used to construct the graph pattern, and the stroke path similarity graph matching method was applied to establish an accurate correspondence between two graph patterns. Finally, according to the matching results, isomorphic triangulations were established for the source and target Chinese characters contours, and morphing animations were generated by using as-rigid-as-possible shape interpolation to the isomorphic triangulations. In the experiment, the stroke path similarity graph matching method was compared with two existing methods, and some morphing animations were also presented. The experimental results show that the proposed method can produce correct correspondence between Chinese characters from different writing stages, and generate smooth deformation animations.
- Chinese characters /
- correspondence /
- graph model matching /
- shape interpolation /
- morphing animation

HTML全文

参考文献(19)

[1]	王宁. 汉字构形史丛书[M].上海:上海教育出版社,2003. Wang N.Series of books:history of Chinese characters'structure[M].Shanghai:Shanghai Education Press,2003(in Chinese).
[2]	Sederberg T W, Greenwood E.A physically based approach to 2D shape blending[C]//ACM Computer Graphics.New York:ACM,1992,26(2):25-34.
[3]	Zhang Y. A fuzzy approach to digital image warping[J].IEEE Computer Graphics and Applications, 1996,16(4):34-41.
[4]	Carmel E, Cohen-Or D.Warp-guided object space morphing[J].The Visual Computer,1997,13(9-10):465-478.
[5]	Yang W W, Feng J Q,Jin X G,et al.2-D shape blending based on visual feature decomposition[C]//Proceedings of Computer Animation and Social Agents,2004:139-146.
[6]	Belongie S, Malik J,Puzicha J.Shape matching and object recognition using shape contexts[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002,24(4):509-522.
[7]	Liu L G, Wang G P,Zhang B,et al.Perceptually based approach for planar shape morphing[C]//12th Pacific Conference on Computer Graphics and Applications.Washington:IEEE,2004:111-120.
[8]	Mortara M, Spagnuolo M.Similarity measures for blending polygonal shapes[J].Computers & Graphics,2001,25(1):13-27.
[9]	Bai X, Latecki L J.Path similarity skeleton graph matching[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(7):1282-1292.
[10]	Myronenko A, Song X.Point set registration:coherent point drift[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(12):2262-2275.
[11]	Lian Z H, Xiao J G.Automatic shape morphing for Chinese characters[C]//SIGGRAPH Asia 2012 Technical Briefs.New York:ACM,2012,2:1-4.
[12]	Alexa M, Cohen-Or D,Levin D.As-rigid-as-possible shape interpolation[C]//Proceedings of the ACM SIGGRAPH Conference on Computer Graphics.New York:ACM,2000:157-164.
[13]	Zhang T, Suen C Y.Fast parallel algorithm for thinning digital patterns[J].Communications of the ACM,1984,27(3):236- 239.
[14]	Shi J B, Tomasi C.Good features to track[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Los Alamitos,CA:IEEE,1994:593-600.
[15]	Torresani L, Kolmogorov V,Rother C.Feature correspondence via graph matching:models and global optimization[C]//Proceedings of the 10th European Conference on Computer Vision.Heidelberg:Springer Verlag,2008:596-609.
[16]	Xia Y, Wu J Q,Gao P C,et al.Ontology-based model for Chinese calligraphy synthesis[J].Computer Graphics Forum,2013 32(7):11-20.
[17]	Chung F, Ip W W S.Complex character decomposition using deformable model[J].IEEE Transactions on Systems,Man and Cybernetics Part C:Applications and Reviews,2001,31(1):126-132.
[18]	Gupta,H, Wenger R.Constructing piecewise linear homeomorphisms of simple polygons[J].Journal of Algorithms,1997,22(1): 142-157.
[19]	Surazhsky V, Gotsman C.High quality compatible triangulations[J].Engineering with Computers,2004:20(2):147-156.