Multi-level adaptive fuzzy filter for mixed noise removal

Combination or hybrid filters utilize linear and nonlinear techniques to remove noise from an image while preserving details. Typically these filters are trained to remove either Gaussian or impulsive noise. They cannot remove large amounts of mixed noise. In this paper we present a new multi-level adaptive fuzzy (MLAF) filter for mixed noise removal during image processing. This filter utilizes fuzzy sets to combine linear and nonlinear techniques and effectively removes large amounts of mixed Gaussian and impulsive noise while preserving the image details. Experimental results are included to demonstrate the effectiveness of the proposed filter