Neural Computation, Vol 7, 408-423, Copyright © 1995 by The MIT Press

ARTICLES

Representation of similarity in three-dimensional object discrimination

S Edelman
Department of Applied Mathematics and Computer Science, Weizmann Institute of Science, Rehovot, Israel.

How does the brain represent visual objects? In simple perceptual generalization tasks, the human visual system performs as if it represents the stimuli in a low-dimensional metric psychological space (Shepard 1987). In theories of three-dimensional (3D) shape recognition, the role of feature-space representations [as opposed to structural (Biederman 1987) or pictorial (Ullman 1989) descriptions] has long been a major point of contention. If shapes are indeed represented as points in a feature space, patterns of perceived similarity among different objects must reflect the structure of this space. The feature space hypothesis can then be tested by presenting subjects with complex parameterized 3D shapes, and by relating the similarities among subjective representations, as revealed in the response data by multidimensional scaling (Shepard 1980), to the objective parameterization of the stimuli. The results of four such tests, accompanied by computational simulations, support the notion that discrimination among 3D objects may rely on a low-dimensional feature space representation, and suggest that this space may be spanned by explicitly encoded class prototypes.

This article has been cited by other articles:

				C. Eckes, J. Triesch, and C. v. d. Malsburg Analysis of cluttered scenes using an elastic matching approach for stereo images. Neural Comput., June 1, 2006; 18(6): 1441 - 1471. [Abstract] [Full Text] [PDF]