A New Filter for Color Images Corrupted by Impulse Noise

Based on an integration of a simple impulse detector and a robust neuro-fuzzy (RNF) network, a new effective filter for color images corrupted by impulse noise is presented in this paper. There are two distinctive properties of the proposed method. The first is the use of a simple impulse detector. The other is the use of a novel membership function in the design of the adaptive RNF network, making the network robust to impulse noise. Extensive simulation results indicate that the proposed filter not only has the ability of noise attenuation but also has desirable robustness.