Contour-Map Encoding of Shape for Early Vision

Contour maps provide a general method for recognizing twodimensional shapes. All but blank images give rise to such maps, and people are good at recognizing objects and shapes from them. The maps are encoded easily in long feature vectors that are suitable for recognition by an associative memory. These properties of contour maps suggest a role for them in early visual perception. The prevalence of direction-sensitive neurons in the visual cortex of mammals supports this view. This research was supported by the National Aeronautics and Space Administrat ion (NASA) with cooperative agreement No. NCC2-387 with the Universities Space Research Association. To appear in D.S. Touretzky (ed.), Advances in Neural Information Processing Systems £. San Mateo, California: Kaufmann, 1990. Contour-Map Encoding of Shape for Early Vision Pentti Kanerva Research Institute for Advanced Computer Science Mail Stop 230-5, NASA Ames Research Center Moffett Field, California 94035