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.2015.0306100
出版社：S&S Publications
摘要：Medical imaging emerges as one of the most important sub-fileds in the world of science andtechnology. There is no compromise in the quality of medical images as it is used to diagnose a variety of illness.Developing a significant denoising method, plays a major role in image processing.In this paper, image is firstdecomposed into eight subbands using 3D DWT and bilateral filter and Thresholding methods are incorporated. Theapproximation coefficient obtained from DWT is filtered using Bilteral filter and the detail coefficients are subjected toWavelet Thresholding. Hard thresholding and Soft threshold are the commonly used thresholding techniques. For betterresults, Bayes shrink, Visushrink etc were used to estimate the threshold value. Image is reconstructed by the inversewavelet transform of the resultant coefficients and then it is filtered using Bilateral filter. MRI images and Ultrasoundimages are taken as datasets for quantitative validation. The Peak Signal to Noise Ratio (PSNR), Root mean squareerror (RMSE), Structural Similarity Index (SSIM) are employed to quantify the performance of denoising
关键词：Image denoising; Multi resolution analysis; 3D DWT; Bilateral Filter; Wavelet Thresholding
