Removal of Salt and Pepper Noise through Modified PSM Filter

Abstract

In this paper, a new Modified Progressive Switching Median filtering algorithm is presented for the removal of salt and pepper noise from corrupted images. It sets a limit on the number of good pixel used in determine median and mean value and substitute to impulse pixel with the summation of its mean value and median value which is divide by 2.02, after that pass through Gaussian filter. This scheme can remove salt and pepper noise with a noise level as high as 90%. Experimental result shows that the proposed filter is superior over the traditional filter in maintaining higher PSNR (Peak Signal to Noise Ratio).