HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Full Text Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Similar articles in this journal Similar articles in PubMed Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via HighWire Citing Articles via Google Scholar Google Scholar Articles by Stringer, S. M. Articles by Rolls, E. T. Search for Related Content PubMed PubMed Citation Articles by Stringer, S. M. Articles by Rolls, E. T.

Invariant Object Recognition in the Visual System with Novel Views of 3D Objects

simon.stringer{at}psy.ox.ac.uk, Oxford University, Centre for Computational Neuroscience, Department of Experimental Psychology, Oxford OX1 3UD, England

Edmund T. Rolls

Edmund.Rolls{at}psy.ox.ac.uk, web: www.cns.ox.ac.uk, Oxford University, Centre for Computational Neuroscience, Department of Experimental Psychology, Oxford OX1 3UD, England

To form view-invariant representations of objects, neurons in the inferior temporal cortex may associate together different views of an object, which tend to occur close together in time under natural viewing conditions. This can be achieved in neuronal network models of this process by using an associative learning rule with a short-term temporal memory trace. It is postulated that within a view, neurons learn representations that enable them to generalize within variations of that view. When three-dimensional (3D) objects are rotated within small angles (up to, e.g., 30 degrees), their surface features undergo geometric distortion due to the change of perspective. In this article, we show how trace learning could solve the problem of in-depth rotation-invariant object recognition by developing representations of the transforms that features undergo when they are on the surfaces of 3D objects. Moreover, we show that having learned how features on 3D objects transform geometrically as the object is rotated in depth, the network can correctly recognize novel 3D variations within a generic view of an object composed of a new combination of previously learned features. These results are demonstrated in simulations of a hierarchical network model (VisNet) of the visual system that show that it can develop representations useful for the recognition of 3D objects by forming perspective-invariant representations to allow generalization within a generic view.

This article has been cited by other articles:

				E. T. Rolls An attractor network in the hippocampus: Theory and neurophysiology Learn. Mem., November 15, 2007; 14(11): 714 - 731. [Abstract] [Full Text] [PDF]

				E. T. Rolls and S. M. Stringer Invariant Global Motion Recognition in the Dorsal Visual System: A Unifying Theory Neural Comput., January 1, 2006; 19(1): 139 - 169. [Abstract] [Full Text] [PDF]