Fuzzy filtering for mixed noise removal during image processing

Presents a new nonlinear fuzzy filter for image processing in a mixed noise environment, where both additive Gaussian noise and nonadditive impulsive noise may be present. Averaging filters can effectively remove the Gaussian noise and order statistics filters or median filters can effectively remove the impulsive noise. However, it is difficult to combine these filters to remove mixed noise in an image processing environment without blurring the image details or edges. Trying to distinguish between noise and edge information in the image is an inherently ambiguous problem and naturally leads to the development of a fuzzy filter. We use local statistics to train the membership function of a fuzzy filter for image processing to remove both Gaussian noise and impulsive noise while preserving edges. We show that such a fuzzy filter gives superior results when compared to averaging filters, median filters, and other fuzzy filters. We also demonstrate the robustness of this filtering technique