基于小波维纳滤波和各项异性扩散的图像去噪  

Image Denoising Based on Wiener Filtering in Wavelet Domain and Anisotropic Diffusion

作　　者：李一亮[1] 王卫卫[1] 

机构地区：[1]西安电子科技大学理学院数学科学系,西安710071

出　　处：《计算机工程与应用》2006年第29期52-54,共3页Computer Engineering and Applications

基　　金：国家自然科学基金资助项目(编号:60272058);国家优秀博士学位论文作者专项基金(编号:200139);教育部高校青年教师奖专项基金

摘　　要：提出一种基于小波和各项异性非线性扩散的新图像去噪算法。小波域局部阈值维纳滤波是一种简单有效的去噪方法,利用该方法先对原始图像进行初步去噪,以此引导非线性扩散模型中的边缘检测函数,再用非线性扩散进行去噪。实验表明:该算法不仅很好地保存了图像的边缘信息,而且有效地去除了图像中的大部分噪声,无论是视觉效果还是客观标准上都优于单纯的小波域维纳滤波或各项异性非线性扩散去噪。A new image denoising method based on wavelet and anisotropic nonlinear diffusion is presented.Among the popular wavelet based image denoising methods,locally Wiener filtering with thresholding is a simple but efficient one. The authors use this scheme to get a cleaner image.Then this cleaner version is used as a guide to get the edge testing function in nonlinear diffusion to reduce noise in the original image.Experimental results show that important features in images,such as edges,can be well recovered and most noise components in uniform parts can be removed.The new method performs well both from the common used objective standards and from visual.

关 键 词：小波 维纳滤波 各项异性非线性扩散 去噪 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]