Detecting instances of shape classes that exhibit variable structure

Abstract. This paper proposes a method for detecting shapes of variable structure in images with clutter. The term “variable structure ” means that some shape parts can be repeated an arbitrary number of times, some parts can be optional, and some parts can have several alternative appearances. The particular variation of the shape structure that occurs in a given image is not known a priori. Existing computer vision methods, including deformable model methods, were not designed to detect shapes of variable structure; they may only be used to detect shapes that can be decomposed into a fixed, a priori known, number of parts. The proposed method can handle both variations in object structure and variations in the shape of object parts. A new class of shape models is introduced, called Hidden State Shape Models, that can naturally represent shapes of variable structure. A detection algorithm is described that finds instances of such shapes in images with large amounts of clutter by finding globally optimal correspondences between image features and object models. Experiments with real images demonstrate that our method can localize plant branches that consist of an a priori unknown number of leaves and can detect hands more accurately than a hand detector based on the chamfer distance. 2 Vassilis Athitsos et al. Fig. 1. Three shape classes that exhibit variable structure: branches with leaves, hair combs, and hand contours. Such classes can be naturally modeled with a Hidden State Shape Model (HSSM).