Image decomposition and enhancement using rank filtering
Pavel A. Chochia · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 1998
An image is considered to be a blend of several statistically and semantically independent components, containing details of different information classes. Discussing about image decomposition we mean the splitting of an image onto the set of these components. Statistical distinctions of them allow to find effective algorithm for decomposition of received image to several components of different properties. It gives the opportunity to extract from an image only the component of interest, to avoid redundant information from the following analysis, and to create decomposition-based image processing methods. In the paper we consider multicomponent model of image fragment, propose rank algorithm for image decomposition, and discuss image enhancement algorithm, being based on the preliminary decomposition.