| 基于结构的纹理合成 |
| |
| 引用本文： | 张蓬,彭思龙.基于结构的纹理合成[J].计算机辅助设计与图形学学报,2004,16(3):290-296. |
| |
| 作者姓名： | 张蓬 彭思龙 |
| |
| 作者单位： | 中国科学院自动化研究所集成电路工程中心,北京 100080 |
| |
| 基金项目： | 国家自然科学基金 ( 60 2 72 0 42 )资助 |
| |
| 摘 要： | 提出一种纹理合成算法，首先将经验模型分解(EMD)算法引入到纹理合成领域，对样本图像的纹理结构进行提取；然后应用分片采样算法和Markov随机场(MRF)模型生成输出纹理的结构，对于结构之间的空白区域，采用距离变换方法分片提取其不规则的形状并进行填充。实验结果表明，该算法不仅简单、快速、合成质量高，而且具有广泛的适用性。
|
| 关 键 词： | 计算机视觉 图形图像处理 纹理合成 直方图匹配 概率密度函数 |
Structure-Based Texture Synthesis |
| |
| Zhang Peng,Peng Silong.Structure-Based Texture Synthesis[J].Journal of Computer-Aided Design & Computer Graphics,2004,16(3):290-296. |
| |
| Authors: | Zhang Peng Peng Silong |
| |
| Abstract: | Inspired by brushwork, we presented a novel algorithm for synthesizing textures from an input sample First, empirical mode decomposition(EMD) algorithm was introduced and texture structure of sample was extracted Second, we synthesized texture structure with patch based sampling and Markov random field(MRF) For the spaces among structures, we extracted their irregular forms with distance transform and filled in them Our method is not only simple, fast, ensures good quality, but also robust |
| |
| Keywords: | texture synthesis patch based sampling empirical mode decomposition Markov random field |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
