Abstracet-Many researchers have proposed that objects are perceived as structural descriptions, which specify the configuration of an object's features (or parts) in terms of their categorical relations to one another. Others have proposed that objects arc perceived as views, which specify the configuration of an object's features in terms of their coordinates, in particular 2D views. This paper presents five experiments testing these competing accounts of the perception of the configuration of

more »

... an object's features. Subjects learned to recognize a set of target objects and were tested for their ability to distinguish them from various distractors that differed either in their categorical relations or their coordinates. Subjects were consistently more likely to confuse both 2D and 3D objects that were similar in their parts' relations to each other than to confuse objects similar in their parts' coordinates (in any reference frame). This effect persisted when subjects were allowed to view the objects as long as they wished and when they were explicitly trained to distinguish them from the distractors. These findings suggest that we perceive an object's features in terms of their categorical relations to one another. A preliminary model of the findings is presented. RELATIONS IN SHAPE PERCEPTION A substantial body of work in both psychology and computer science is addressed to understanding the representations underlying human shape perception and object recognition. A representation of object shape is characterized by at least three independent attributes (see Palmer, 1978; Tarr, 1995) : a reference frame (e.g. viewer-or object-centered); a collection of primitive elements or 'features' (e.g. Gabor wavelets, lines and vertices, volumetric parts, etc.); and a set of relations for specifying the primitives' configuration inside the reference frame (e.g. relative to one another or relative to the origin of the reference frame). The reference frames and primitives serving human shape perception have been the subject of a substantial body of research (see Biederman,