ORDER-STATISTICS IN DIGITAL IMAGE-PROCESSING

In recent years significant advances have been made in the development of nonlinear image processing techniques. Such techniques are used in digital image filtering, image enhancement, and edge detection. One of the most important families of nonlinear image filters is based on order statistics. The widely used median filter is the best known filter of this family. Nonlinear filters based on order statistics have excellent robustness properties in the presence of impulsive noise. They tend to preserve edge information, which is very important to human perception. Their computation is relatively easy and fast compared with some linear filters. All these features make them very popular in the image processing community. Their theoretical analysis is relatively difficult compared with that of the linear filters. However, several new tools have been developed in recent years that make this analysis easier. In this review paper an analysis of their properties as well as their algorithmic computation will be presented