基于各向异性扩散的图像降噪算法综述  

Image noise reduction based on anisotropic diffusion:A survey

作　　者：余锦华[1] 汪源源[1] 

机构地区：[1]复旦大学电子工程系,上海200433

出　　处：《电子测量与仪器学报》2011年第2期105-116,共12页Journal of Electronic Measurement and Instrumentation

基　　金：国家自然科学基金(编号:30570488)资助项目;上海市优秀学科带头人计划(编号:10XD1400600)资助项目

摘　　要：系统介绍了基于各向异性扩散的图像降噪技术的发展。将各向异性扩散模型分为针对普通噪声和斑点噪声降噪两大类,阐述了在其发展过程中出现的较典型模型的原理、方法和特点。通过试验全面比较了这些模型在降噪、边缘定位、结构保持方面的优劣,分析了该领域亟待解决的关键问题和发展趋势。A comprehensive review is presented for the development of the anisotropic diffusion （AD） in image noise reduction. The various AD models are classified into two categories： the one for normal noise reduction and the other for speckle noise reduction. During the development of the AD technique, several typical models are highlighted in their principle, method and characteristics. From experiments, the performances of these AD models are comprehensively compared in terms of noise reduction, edge localization and structure preservation. Key problems expected to be solved and future development trends are discussed for the AD technique in image denoising.

关 键 词：各向异性扩散 降噪 高斯噪声 脉冲噪声 斑点噪声 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] R319[自动化与计算机技术—计算机科学与技术]