On the representation of image structures via scale space entropy conditions

This gager deals with a novel way for representing and computing image feat ures encapsulated within different regions of scale-space. Employing a ther modynamical model for scale-space generation, the method derives features a s those corresponding to "entropy rich" image regions where, within a given range of spatial scales, the entropy gradient remains constant. Different types of image features, defining regions of different information content, are accordingly encoded by such regions within different bands of spatial scale.