Abstract: Image Processing plays an important role in the fields of consumer electronics, information technology, computer science etc. As digital image processing use certain algorithms on the input data to produce enhanced image. But noise will degrade the quality of image such as salt and pepper noise, Gaussian noise etc. To improve the quality of images as well as compression of images is to be done by using large number of algorithms. The main objective of this paper is the removal or reduction of degradations that are incurred while the image is being obtained using image restoration. For this it proposes an image restoration model using sparse coding representation and patch group using K-Means PCA Analysis which will reduce the noise to a greater extent by improving PSNR value of image. All simulations will be done in MATLAB R2013a.

Keywords: Image Processing, Gaussian noise, MATLAB, PCA Analysis, PSNR value.