The Role of Shape in Visual Recognition

Abstract Visual recognition requires a robust representation of typical object char-acteristics. Among all visual characteristics, shape plays a special role. It exhibits crucial invariance properties and captures the holistic structure of objects. However, shape cannot be extracted directly from an image, as it is an emergent property. Thus, representing shape is challenging, since it is related to several key problems of computer vision, such as grouping, segmentation, and correspondence problems. This paper reviews the development of shape in object recognition so far, discusses the reasons for the underlying developmental trends, and presents some promising recent contributions that point towards more accurate models of object structure. 1 Regularity, Structure, and Form Our interaction with the world is constantly defined by the structure and charac-teristics of the objects around us, in particular by their form. This is only possible since our world exhibits an astounding degree of regularity. Let us now survey the prevalence of structure and the implications this has on cognition. Regardless, what scale we observe our universe on, order and regularity are evident everywhere. O