Medical Image Denoising Based on Multi Resolution Analysis Using Wavelet

Image denoising is one of the most important steps in image and video processing applications. Digital images are corrupted by various types of noises during acquisition and transmission in the channel. In this paper, an approach for image denoising based on Stationary Wavelet Transform (SWT) and Discrete Wavelet Transform (DWT) is proposed. The noises are removed by soft threshold the high frequencies sub-bands of SWT and DWT. Then the high frequencies sub-bands of DWT are interpolated by using bicubic interpolation technique and added to the high frequencies sub-bands of SWT in order to get the modified noise free sub-bands. Then all these sub-bands are combined with the low frequency sub-band of SWT to obtain the de-noised image by using inverse SWT (ISWT). Experimental results show that the proposed method gives better PSNR values than the DWT based soft shrinkage as well as preserves the image edge information.