preprint - Complex Cells and Object Recognition

[Shimon Edelman]

Title:		Complex Cells and Object Recognition
Authors:	Shimon Edelman, Nathan Intrator, Tomaso Poggio
ftp  URL:	ftp://eris.wisdom.weizmann.ac.il/pub/edelman/nips97.ps.Z
http URL:	http://www.ai.mit.edu/~edelman/mirror/nips97.ps.Z

Abstract:

Nearest-neighbor correlation-based similarity computation in the space
of outputs of complex-type receptive fields can support robust
recognition of 3D objects. Our experiments with four collections of
objects resulted in mean recognition rates between 84% (for
subordinate-level discrimination among 15 quadruped animal shapes) and
94% (for basic-level recognition of 20 everyday objects), over a 
40deg X 40deg range of viewpoints, centered on a stored canonical view
and related to it by rotations in depth. This result has interesting
implications for the design of a front end to an artificial object
recognition system, and for the understanding of the faculty of object
recognition in primate vision.
------------------------------------------------------------------------

Comments welcome.

-Shimon

Dr. Shimon Edelman,  Center for Biol & Comp Learning, MIT
DELENDA BIBI               http://www.ai.mit.edu/~edelman
fax: (+1) 617 253-2964  tel: 253-6357  edelman at ai.mit.edu