A Novel Variable Mask Median Filter for Removal of Random Valued Impulses in Digital Images (VMM)

This paper presents a novel technique for de noising the images which are corrupted by random valued impulse noise. The detection of noisy pixels is done using variable weights of all neighbor directional pixels through 5 x 5 mask. The proposed operator performs arithmetic absolute differences along with some other arithmetic operations on the pixels aligned in the four main directions with the center pixel to classify test pixel. For filtering we have used an improved median based filtering technique which uses variable mask consisting of nine and twenty five pixels respectively. Certain pixels in the 3 x 3 window are selected prior to compute median operation. Three user supplied parameters are varied in a wide range to obtain the optimal results. The results obtained using the implementation show better de noising capability along with preservation of fine image textures/ details for the images corrupted with random valued impulses.