2 PIXEL-PRESELECTION METHODS FOR MEDIAN-TYPE FILTERING

Most of the median-type filters designed to remove impulsive noise pro cess all the pixels in the noisy image. A certain number of non-noisy pixels are thus unexpectedly modified, thereby limiting the quality of the result. Since these pixels need not, and should not, be filtered, the authors propose two approaches for selecting the pixels to be pro cessed. The first of these operates online, by relaxing the order stat istic for pixel substitution, this is known as the relaxed-median filt er. The second approach requires the construction of a mask to determi ne a priori which pixels are to be processed, this is known as the mas k-median filter. The mask is built using some prior information about the class of images at hand.