Generalized Vector Median Filter
Bogdan Smołka, Michal Perczak · International symposium on image and signal processing and analysis/ISPA ... · 2007
In this contribution we analyze the properties of a novel class of noise attenuating and edge enhancing filters for color image processing. The new filtering design is a generalization of the well known Vector Median Filter. The new filter class is minimizing the cumulated dissimilarity measure of a cluster of pixels belonging to the sliding filtering window and outputs the pixel centrally located within the so called peer group of pixels. The described filter is computationally efficient, easy to implement and very effective in suppressing impulsive noise, while preserving image details and strongly enhancing its edges.