Image Segmentation and Uncertainty

Presents the first unified theory of image segmentation, written by the winners of the 1985 Pattern Recognition Society medal. Until now, image processing algorithms have always been beset by uncertainties, no one method proving completely satisfactory. Wilson and Spann tackle the problem of uncertainty head-on. They describe a new class of algorithms (based, in part, on quadtrees) and demonstrate their applications, including grey level and texture segmentation. These algorithms produce excellent results in a wide range of synthetic and natural data. Provides many examples of applications from medicine to remote sensing.