期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2015
卷号：3
期号：6
DOI：10.15680/ijircce.2015.0306017
出版社：S&S Publications
摘要：Image denoising constitutes the first step in image processing domain. In order to solve this frequentlyoccurring problem various methods have been proposed. In this paper a denoising algorithm is proposed which uses thecombination of Fast Non-Local means filter (FNLM) and adaptive wavelet thresholding. The performance of FNLMfilter deteriorates with the increase of noise amount in the image. This hybrid approach solves this problem. Firstly, theimage is denoised by the FNLM filter and then its method noise is obtained. The method noise is subjected to adaptivewavelet thresholding for extracting the image details that were removed by the FNLM filter. These extracted details areadded to the output of FNLM filter and a noise free image is recovered with all the edges and image details preserved
关键词：adaptive thresholding; method noise; BayesShrink; fast non local means
