Local edge direction based non-local means for image denoising

作     者：JIA Li-na JIAO Feng-yuan LIU Rui-qiang GUI Zhi-guo 贾丽娜;焦枫媛;刘瑞强;桂志国

作者机构：Department of Electronic Information Engineering Shanxi University Taiyuan 030013 China Shanxi Provincial Key Laboratory for Biomedical Imaging and Big DataNorth University of China Taiyuan 030051 China School of Electronics and Information Engineering Harbin Institute of Technology Harbin 150001 China 

出 版 物：《Journal of Measurement Science and Instrumentation》 (测试科学与仪器（英文版）)

年 卷 期：2019年第10卷第3期

页      面：236-240页

核心收录：

学科分类：0711[理学-系统科学] 07[理学] 08[工学] 080401[工学-精密仪器及机械] 0804[工学-仪器科学与技术] 080402[工学-测试计量技术及仪器] 

基　　金：National Key Research and Development Program of China(No.2016YFC0101601) Fund for Shanxi“1331 Project”Key Innovative Research Team Shanxi Province Science Foundation for Youths(No.201601D021080) Universities Science and Technology Innovation Project of Shanxi Province(No.2017107) 

主　　题：image denoising neighborhood filter non-local means (NLM) steering kernel regression (SKR) 

摘      要：Classic non-local means (CNLM) algorithm uses the inherent self-similarity in images for noise removal. The denoised pixel value is estimated through the weighted average of all the pixels in its non-local neighborhood. In the CNLM algorithm, the differences between the pixel value and the distance of the pixel to the center are both taken into consideration to calculate the weighting coefficients. However, the Gaussian kernel cannot reflect the information of edge and structure due to its isotropy, and it has poor performance in flat regions. In this paper, an improved non-local means algorithm based on local edge direction is presented for image denoising. In edge and structure regions, the steering kernel regression (SKR) coefficients are used to calculate the weights, and in flat regions the average kernel is used. Experiments show that the proposed algorithm can effectively protect edge and structure while removing noises better when compared with the CNLM algorithm.