Abstract
We explore representation of 3D objects in which several distinct 2D views are stored for each object. We demonstrate the ability of a two-layer network of thresholded summation units to support such representations. Using unsupervised Hebbian relaxation, the network learned to recognize ten objects from different viewpoints. The training process led to the emergence of compact representations of the specific input views. When tested on novel views of the same objects, the network exhibited a substantial generalization capability. In simulated psychophysical experiments, the network's behavior was qualitatively similar to that of human subjects.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Barlow HB (1985) Cerebral cortex as model builder. In: Rose D, Dobson VG (eds) Models of the visual cortex. Wiley, New York, pp 37–46
Damasio AR (1989) The brain binds entities and events by multiregional activation from convergence zones. Neural Comput 1:123–132
Edelman GM, Finkel L (1984) Neuronal group selection in the cerebral cortex. In: Edelman GM, Gall WE, Cowan WM (eds) Dynamical aspects of neocortical function. Wiley, New York, pp 653–695
Edelman S, Bülthoff HH, Weinshall D (1989) Stimulus familiarity determines recognition strategy for novel 3D objects. A. I. Memo No. 1138, AI Lab, MIT
Edelman S, Bülthoff HH (1990) Viewpoint-specific representations in 3D object recognition. A.I. Memo No. 1239, AI Lab, MIT
Foster DH (1973) A hypothesis connecting visual pattern recognition and apparent motion. Kybernetik 13:151–154
Fukushima K (1988) Neocognitron: a hierarchical neural network capable of visual pattern recognition. Neural Networks 1:119–130
Gilbert CD (1988) Neuronal and synaptic organization in the cortex. In: Rakic P, Singer W (eds) Neurobiology of neocortex. Wiley, New York, pp 219–240
Jolicoeur P (1985) The time to name disoriented objects. Memory Cogn 13:289–303
Kandel ER, Schwartz JH (1985) Principles of neural science. Elsevier, New York
Koch C, Ullman S (1985) Selecting one among the many: a simple network implementing shifts in selective visual attention. Hum Neurobiol 4:219–227
Koriat A, Norman J (1985) Mental rotation and visual familiarity. Percept Psychophys 37:429–439
Larsen A (1985) Pattern matching: effects of size ratio, angular difference in orientation and familiarity. Percept Psychophys 38:63–68
Lowe DG (1986) Perceptual organization and visual recognition. Kluwer, Boston
Mallot HA, Bülthoff HH, Little JJ (1989) Neural architecture for optical flow computation. A.I. Memo No. 1067, AI Lab, MIT
McCulloch WS (1950) Brain and behavior. In: Halstead WC (eds) Comparative Psychology Monograph, vol 20. University of California Press, Berkeley, Calif, pp 39–50
McNaughton BL, Morris RGM (1987) Hippocampal synaptic enhancement and information storage within a distributed memory system. Trends Neurosci 10:408–415
Merzenich MM, Recanzone G, Jenkins WM, Allard TT, Nudo RJ (1988) Cortical representation plasticity. In: Rakic P, Singer W (eds) Neurobiology of neocortex. Wiley, New York, pp 41–68
Morton J (1969) Interaction of information in word recognition. Psychol Rev 76:165–178
Palmer SE, Rosch E, Chase P (1981) Canonical perspective and the perception of objects. In: Long J, Baddeley A (eds) Attention and performance, vol IX. Erlbaum, Hillsdale, NJ, pp 135–151
Perrett DI, Mistlin AJ, Chitty AJ (1989) Visual neurones responsive to faces. Trends Neurosci 10:358–364
Poggio T, Edelman S (1990) A network that learns to recognize three-dimensional objects. Nature 343:263–266
Poggio T, Girosi F (1990) Regularization algorithms for learning that are equivalent to multilayer networks. Science 247:978–982
Poggio T, Torre V, Koch C (1985) Computational vision and regularization theory. Nature 317:314–319
Ratcliff R (1981) Parallel processing mechanisms and processing of organized information in human memory. In: Anderson JA, Hinton GE (eds) Parallel models of associative memory. Erlbaum, Hillsdale, NJ
Rock I, DiVita J (1987) A case of viewer-centered object perception. Cogn Psychol 19:280–293
Rock I, Wheeler D, Tudor L (1989) Can we imagine how objects look from other viewpoints? Cogn Psychol 21:185–210
Shepard RN, Cooper LA (1982) Mental images and their transformations. MIT Press, Cambridge, Mass
Tarr M, Pinker S (1989) Mental rotation and orientation-dependence in shape recognition. Cogn Psychol 21:233–282
Thompson DW, Mundy JL (1987) Three-dimensional model matching from an unconstrained viewpoint. In: Proceedings of IEEE Conference on Robotics and Automation. Raleigh, NC, pp 208–220
Ullman S (1979) The interpretation of visual motion. MIT Press, Cambridge, Mass
Ullman S (1989) Aligning pictorial descriptions: an approach to object recognition. Cognition 32:193–254
Ullman S, Basri R (1990) Recognition by linear combinations of models. A.I. Memo No. 1152, AI Lab, MIT
Von der Malsburg C, Singer W (1988) Principles of cortical network organization. In: Rakic P, Singer W (eds) Neurobiology of neocortex. Wiley, New York, pp 69–100
Yuille AL, Grzywacz NM (1989) A winner-take-all mechanism based on presynaptic inhibition feedback. Neural Comput 1:334–347
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Edelman, S., Weinshall, D. A self-organizing multiple-view representation of 3D objects. Biol. Cybern. 64, 209–219 (1991). https://doi.org/10.1007/BF00201981
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF00201981