| 基于小世界模型和图论的图像去噪 |
| |
| 引用本文： | 刘国金.基于小世界模型和图论的图像去噪[J].光电子．激光,2010(1):149-153. |
| |
| 作者姓名： | 刘国金 |
| |
| 作者单位： | 重庆大学通信工程学院; |
| |
| 基金项目： | 教育部高等学校博士学科点科研基金资助项目(20070611013);;重庆市自然科学基金资助项目(CSTC,2009BB2358,2008BB2164);;重庆大学研究生创新基金资助项目(200909C1015,200911A1A0030319) |
| |
| 摘 要： | 提出了一种基于图论的偏微分方程(PDE)图像去噪方法。在构造图的拓扑结构过程中,引入了小世界模型,降低图的直径,加快算法的收敛速度。同时,评估了图的权重函数中最优参数的选取。最后,用图的拉普拉斯矩阵和图上的热扩散方程实现图像的去噪。仿真实验结果表明,本文提出的方法能够有效去除高斯噪声,较完整地保持图像中的边缘等细节信息,在去噪性能和算法收敛速率上优于其它的PDE去噪方法。
|
| 关 键 词： | 小世界模型 图论 图像去噪 热扩散方程 |
Image denoising based on graph theory and small world |
| |
| LIU Guo-jin.Image denoising based on graph theory and small world[J].Journal of Optoelectronics·laser,2010(1):149-153. |
| |
| Authors: | LIU Guo-jin |
| |
| Affiliation: | College of Communication Engineering;Chongqing University;Chongqing 400030;China |
| |
| Abstract: | A novel partial differential equation method for image denoising is proposed based on graph theory.In the process of constructing graph,the small world model is introduced into the graph topology to decrease the diameter of graph,which speeds up the denoisng algorithm.Meanwhile,the optimal parameter selection in graph weighting function is studied.After that,the heat diffusion equation and Lapician matrix on the graph are used to filter the noisy image.Experiments illustrate that compared with some existing... |
| |
| Keywords: | small world graph theory image denoising heat diffusion equation |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《光电子．激光》浏览原始摘要信息 |
|
点击此处可从《光电子．激光》下载全文 |
|
