A Filtering Method for Images Based on Edge Detection

As to the gray scales images corrupted by impulse noise, a new noise filtering method is presented. The proposed filter is constructed by combining a median filter, an edge detector, and an adaptive neuro-fuzzy inference system (ANFIS). The proposed noise filter consists of two modes of operation, namely, training and testing (filtering). As demonstrated by the experimental results, the proposed filter not only has the ability of noise attenuation but also possesses desirable capability of details preservation. It significantly outperforms other conventional filters.