文献类型：期刊文献

中文题名：A Non Local Feature-Preserving Strategy for Image Denoising

英文题名：A Non Local Feature-Preserving Strategy for Image Denoising

作者：He Ning[1];Lu Ke[2]

第一作者：何宁

通讯作者：He, N[1]

机构：[1]Beijing Union Univ, Sch Informat, Beijing 100101, Peoples R China;[2]Chinese Acad Sci, Coll Comp & Commun Engn, Grad Univ, Beijing 100049, Peoples R China

第一机构：北京联合大学智慧城市学院

通讯机构：[1]corresponding author), Beijing Union Univ, Sch Informat, Beijing 100101, Peoples R China.|[1141734]北京联合大学智慧城市学院;[11417]北京联合大学;

年份：2012

卷号：21

期号：4

起止页码：651-656

中文期刊名：电子学报：英文版

外文期刊名：CHINESE JOURNAL OF ELECTRONICS

收录：CSTPCD;;EI(收录号：20124615657823);Scopus(收录号：2-s2.0-84868534836);WOS:【SCI-EXPANDED(收录号:WOS:000310669100015)】；

基金：Manuscript Received Sept. 2011; Accepted Oct. 2011. This work is supported by the National Natural Science Foundation of China (No.61070120, No.61103130, No.60982145), Beijing Natural Science Foundation (No.4112021), Beijing Educational Commission Science Foundation (No.KM201111417015), the Opening Project of Shanghai Key Laboratory of Integrate Administration Technologies for Information Security (No.AGK2010005), the National Basic Research Program of China (973 Programs) (No.2010CB731804-1, No.2011CB706901-4).

语种：英文

中文关键词：图像去噪;局部特征;拉格朗日方程;降噪方法;图像噪声;修补程序;全球信息;总变分

外文关键词：Feature-preserving; Image denoising; Non-local means; Regularization

摘要：In this paper, we propose a variational image denoising model by exploiting an adaptive feature-preserving strategy which is derived from the Non-local means (NL-means) denoising approach. The commonly used NL-means filter is not optimal for noisy images containing small features of interest since image noise always makes it difficult to estimate the correct coefficients for averaging, leading to over-smoothing and other artifacts. We address this problem by a non-local detail preserving constraint, which is performed by adding two terms in the Total variation (TV) model. One is a non local patch based regularization term that controls the amount of denoising to preserve textures, small details, or global information, the other is a new data fidelity term, which forces the gradients of desired image being close to the smoothed normal. The Euler-Lagrange equation is used to solve the problem. Experimental results show that the proposed method can alleviate the over-smoothing effect and other artifacts, while preserving the fine details.