Mixed Gaussian and Impulsive Noise removal using Morphological Contrast detector

Abstract

Major stage in digital image processing is image denoising. In this paper, gray scale image denoising is presented using mathematical morphology. In this proposed method Gaussian noise and salt pepper noise is added for original image. To denoise noisy image, basic operations of morphology like dilation, erosion, opening, and closing are used. With this basic operation disk structuring element is imposed on noisy image to improve the quality of the image. Top-hat transform is also used to denoise noisy image with same structuring element. Assessment parameters like mean square error and peak signal to noise ratio indicates that, proposed work yields better  results when compared to other filters.