creators_name: Edelman, Shimon
creators_name: Intrator, Nathan
creators_name: Poggio, Tomaso
type: preprint
datestamp: 1997-10-17
lastmod: 2011-03-11 08:54:04
metadata_visibility: show
title: Complex cells and Object Recognition
ispublished: unpub
subjects: cog-psy
full_text_status: public
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 (comparable figures were obtained for image-plane translations). 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.
date: 1997
date_type: published
refereed: FALSE
citation:   Edelman, Shimon and Intrator, Nathan and Poggio, Tomaso  (1997) Complex cells and Object Recognition.  [Preprint]    (Unpublished)  
document_url: http://cogprints.org/561/2/199710003.ps