中北大学学报（自然科学版）2018，Vol.39Issue(1)：69-73,5.DOI:10.3969/j.issn.1673-3193.2018.01.012
基于梯度方向的非局部均值图像去噪算法
Non-Local Means Image Denoising Algorithm Based on Gradient Direction
摘要
Abstract
The conventional non-local means denoising algorithm ignored the difference between the gray values of the neighborhood of pixels,resulting in image edge blur and details loss.Therefore,by using the property that a noise-free neighborhood will have similar gradient direction with the same neighbor-hoods but with additive noise,a non-local means image denoising algorithm based on gradient direction was proposed.Firstly,the noise image was preprocessed by Gaussian filtering;secondly,making full use of the regional gradient direction information and the gray value among the image neighborhoods to jointly determine the weight,the proposed method obtained better similarity judgment to improve the traditional non-local means filtering algorithm.Experimental results show that,compared with tradi-tional non-local means denoising algorithm,the new algorithm can effectively maintain the image edge details and other information,which improves the denoising performance of traditional non-local means algorithm and achieves good denoising results.关键词
图像去噪/非局部均值/梯度方向/高斯滤波Key words
image denoising/non-local means/gradient direction/Gaussian filtering分类
信息技术与安全科学引用本文复制引用
苗璐,张权,侯红花,赵明,桂志国..基于梯度方向的非局部均值图像去噪算法[J].中北大学学报（自然科学版）,2018,39(1):69-73,5.基金项目
国家自然科学基金资助项目(61671413) （61671413）
国家重大科学仪器设备开发专项资助项目(2014YQ24044508) （2014YQ24044508）
山西省自然科学基金资助项目(2015011046) （2015011046）
