A new kind of impulse noise filter based on PCNN

Abstract

Median filter can inhibit the impulse noise in the image, but it always erodes or dilates the edges of images. H.S. Ranganath mentioned that impulse noise could be removed through modifying the intensity of those contaminated pixels step by step using PCNN. Obviusly, this method consumes much more time in computation. Combining the PCNN model with the median filter, this paper presents an impulse noise filter based on a simplified PCNN model which has less parameters. Not only can it remove the impulse noise effectively, but it also keeps the details of the images as much as possible. It can be verified through experiments and theoretical analysis that this kind of filter is superior to the normal median filter and the filter mentioned by H.S. Ranganath, whether in the aspect of noise removal or of keeping details.