Nonlocal total variation models for multiplicative noise removal using split Bregman iteration
Nonlocal total variation models for multiplicative noise removal using split Bregman iteration
复制标题
使用分裂 Bregman 迭代消除乘性噪声的非局部全变分模型
DOI：
10.1016/j.mcm.2011.09.021
复制
发表时间：
2012-02-01
影响因子：
--
通讯作者：
Kong, De-Xing
中科院分区：
文献类型：
--
作者：
Dong, Fangfang;Zhang, Haili;Kong, De-Xing
在本文中，非局部全变分（TV）范数被用于乘性噪声去除。非局部TV范数相较于经典TV范数的一个主要优势在于其在处理更好的纹理和重复结构方面的优越性。采用分裂布雷格曼迭代来实现所提出的模型。此外，为了提高我们其中一个模型的性能，我们像在TV去噪模型中一样使用布雷格曼迭代。一组实验表明，所提出的方法比其他一些方法能产生更好的结果。© 2011爱思唯尔有限公司。保留所有权利。
In this paper, the nonlocal total variation (TV) norm is employed for multiplicative noise removal. A main advantage of nonlocal TV norm over classical TV norm is the superiority in dealing with better textures and repetitive structures. Split Bregman iterations are used to implement the proposed models. What is more, to improve the performance of one of our models, we use the Bregman iteration as in the TV denoising model. A set of experiments show that the proposed methods yield better results than some other methods. (C) 2011 Elsevier Ltd. All rights reserved.