基于非局部扩散的图像去噪  

Image Denoising Based on Nonlocal Diffusion

作　　者：王卫卫[1] 韩雨[1] 冯象初[1] 

机构地区：[1]西安电子科技大学理学院数学系,陕西西安710071

出　　处：《光学学报》2010年第2期373-377,共5页Acta Optica Sinica

基　　金：国家自然科学基金(60872138)资助课题

摘　　要：利用空间非局部梯度构造了图像的非局部结构张量,通过对非局部结构张量的特征分解得到图像的一个特征空间,依据特征空间的特性设计了非局部扩散张量,建立了基于非局部扩散张量的各向异性扩散模型。该模型和局部各向异性扩散模型的本质不同在于,在扩散的过程中充分利用了图像的全局信息。优点是在去除噪声的同时,能更好地保护图像的边缘,尤其是纹理等图像的重要细节特征。The nonlocal structure tensor of images is defined by using the nonlocal spatial gradients. The eigenvectors of the nonlocal structure tensor consist in a characteristic space for the image,based on which the nonlocal diffusion tensor is constructed. Utilizing the nonlocal diffusion tensor,the nonlocal anisotropic diffusion model for image denoising is introduced. The model differs from the local anisotropic diffusion model in that,not only neighboring pixels but also pixels far away with similar intensities are concerned. The main advantage of taking those pixels far away but with similar intensities into consideration is that the model protects edges and textures much better than the local model.

关 键 词：图像处理 非局部算子 扩散张量 去噪 纹理结构 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]