Description

Image denoising is an important image processing task, both as a process itself and as a component in other processes. Very many ways to denoise an image or a set of data exists. The main properties of a good image denoising model is that it will remove noise while preserving edges. Traditionally, linear models have been used. Traditionally, linear models have been used. One common approach is to use a Gaussian filter, or equivalently solving the heat-equation with the noisy image as input-data, i.e. a linear, 2nd order PDE-model. For some purposes this kind of denoising is adequate. While some denoising approaches such as the bilateral filter, LARK and NLM estimate each pixel separately fusing other “similar” neighborhood pixel. Some other recent state-of-the-art patch-based methods such as BM3D and PLOW denoise a group of similar patches together. This patch-based methods are inherently limited in performance In this paper Rician Image is added with MEDICAL image to make the Rician MEDICAL image. Both clustering and denoising are performed on image patches. Then the despeckling process implemented based on the PCA with LMMSE filtering. First perform the clustering process to resist the influence of noise by reducing the dimensionality. Principal component analysis is implemented to reduce dimensionality and it leads to perform the k-means clustering algorithm. For denoising process LMMSE filter denoising model proposed. Finally obtain the denoised medical image