Region Adaptive Fuzzy Filter: An Approach for Removal of Random-Valued Impulse Noise

This paper proposes region adaptive fuzzy filter for removal of random-valued impulse noise (RVIN) from color images. It is observed from existing literature that the filter performance increases with improved accuracy of noise detection and better adaption of the filter parameters. Improved minimum mean value detection mechanism is proposed for better classification of noisy and nonnoisy pixels in context to the removal of RVIN from color images. The modified fuzzy filter considers the correlation among the color channels and recursively adapts itself in accordance with the local noise densities. This filter incorporates an adaption technique to determine the maximum allowable window size used during fuzzification and filtering. Rather than one efficient filtering step that has a potential for losing information, region selective second iteration of the filter is applied on highly corrupted regions so as to preserve more image details. Experimental results suggest that the proposed filter provides improved performance in terms of peak signal to noise ratio, normalized color difference, structural similarity index, feature similarity index for color images, and perceptual similarity than most of the state-of-the-art filters.