Evidential reasoning in a pixel classification hierarchy—a potential method for integrating image classifiers and expert system rules based on geographic context

Abstract

This Letter presents a technique for integrating diverse sources of evidence about pixel or segment classification using the belief function approach of the Dempster-Shafer theory of evidential reasoning. A description of the algorithm is provided and a case study is given to illustrate the potential of the method for combining output from image classifiers, geographic information systems and expert system rules concerning geographic context.