Are object shape primitives learnable?

Despite extensive efforts focusing on the recovery of shape primitives (or "geons") in the vision community and despite the large body of psychophysic al studies strongly suggesting the importance of such representation for th e visual system, no model has yet addressed the development of such represe ntations. We propose a developmental architecture, based on the existing ex perimental evidence on human visual development, and present an algorithm w hich illustrates how geons (such as cylinder, cone, cube etc.) may be learn ed. The algorithm learns 2D projections of geons as partial matches between several images. The learning algorithm is based on topographic matching an d cross-correlation methods, and uses no a priori knowledge about the struc ture of geons or any non-local feature. (C) 1999 Elsevier Science B.V. All rights reserved.