|
|||||
|
|
| 基于图论优化的块采样纹理合成 | |
| 引用本文： | 伍博,王燕,刘晓云.基于图论优化的块采样纹理合成[J].计算机工程,2008,34(18):212-214. |
| 作者姓名： | 伍博 王燕 刘晓云 |
| 作者单位： | 1. 成都电子科技大学自动化工程学院,成都,610054;中国科学院深圳先进技术研究院,深圳,518000 2. 河南师范大学物理与信息工程学院,新乡,453007 3. 成都电子科技大学自动化工程学院,成都,610054 |
| 摘 要： | 基于马尔可夫随机场(MRF)模型和已有的块采样合成技术，提出一种改进的合成算法，采用图论的最小割线算法对MRF的似然性进行优化，将合成时的光栅扫描方式改为之字形扫描方式，以抑制纹理的倾向性和纹元的不完整性。试验证明，该算法的合成效果较好。 |
| 关 键 词： | 纹理合成 马尔可夫随机场 最小割线 最大流 |
| 修稿时间： | |
Optimized Patch-based Sampling Texture Synthesis Based on Graph Theory |
|
| WU Bo,WANG Yan,LIU Xiao-yun.Optimized Patch-based Sampling Texture Synthesis Based on Graph Theory[J].Computer Engineering,2008,34(18):212-214. | |
| Authors: | WU Bo WANG Yan LIU Xiao-yun |
| Affiliation: | (1. College of Automation Engineering, University of Electronic Science and Technology of China, Chengdu 610054; 2. Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518000; 3. College of Physical and Information Engineering, Henan Normal University, Xinxiang 453007) |
| Abstract: | This paper proposes a new patch-based sample texture synthesis algorithm based on Markov Random Field(MRF) model and otherrelated algorithms.In the new algorithm, the min-cut algorithm of graph theory is adopted to optimize the likelihood of MRF and improves thescanning method from raster scanning to zigzag scanning.The new scanning method can restrain texel's imperfection and texture's orientation. |
| Keywords: | texture synthesis Markov Random Field(MRF) min-cut max-flow |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |
| 点击此处可从《计算机工程》浏览原始摘要信息 | |
| 点击此处可从《计算机工程》下载全文 | |