Journal home
Advance online publication
Current issue
Archive
Press releases
Supplements
Focuses
Guide to authors
Online submissionOnline submission
Permissions
For referees
Free online issue
Contact the journal
Subscribe
Advertising
work@npg
naturereprints
About this site
For librarians
 
NPG Resources
Nature
Nature Reviews Neuroscience
Nature Cell Biology
Nature Medicine
Neuroscience Gateway
UCSD-Nature Signaling Gateway
NPG Subject areas
Biotechnology
Cancer
Chemistry
Clinical Medicine
Dentistry
Development
Drug Discovery
Earth Sciences
Evolution & Ecology
Genetics
Immunology
Materials Science
Medical Research
Microbiology
Molecular Cell Biology
Neuroscience
Pharmacology
Physics
Browse all publications
Scientific Correspondence
Nature Neuroscience  1, 275 - 277 (1998)
doi:10.1038/1089

Three-dimensional object recognition is viewpoint dependent

Michael J. Tarr1, Pepper Williams2, William G. Hayward3 & Isabel Gauthier4

1  Brown University, Department of Cognitive and Linguistic Sciences, Box 1978, Providence, Rhode Island 02912, USA

2  University of Massachusetts, Department of Psychology , 100 Morrissey Boulevard, Boston, Massachusetts 02125-3393, USA

3  University of Wollongong, Department of Psychology , Northfields Avenue, Wollongong, NSW 2552, Australia

4  Yale University, Department of Psychology, PO Box 208205, New Haven, Connecticut 06520-8205 , USA

Correspondence should be addressed to Michael J. Tarr Michael_Tarr@brown.edu
The human visual system is faced with the computationally difficult problem of achieving object constancy: identifying three-dimensional (3D) objects via two-dimensional (2D) retinal images that may be altered when the same object is seen from different viewpoints1. A widely accepted class of theories holds that we first reconstruct a description of the object's 3D structure from the retinal image, then match this representation to a remembered structural description. If the same structural description is reconstructed from every possible view of an object, object constancy will be obtained. For example, in Biederman's2 oft-cited recognition-by-components (RBC) theory, structural descriptions are composed of sets of simple 3D volumes called geons (Fig. 1), along with the spatial relations in which the geons are placed. Thus a mug is represented in RBC as a noodle attached to the side of a cylinder, and a suitcase as a noodle attached to the top of a brick. The attraction of geons is that, unlike more complex objects, they possess a small set of defining properties that appear in their 2D projections when viewed from almost any position (e.g., all three views of the brick in Fig. 1 include a straight main axis, parallel edges, and a straight cross section). According to the RBC theory, a complex object can therefore be recognized from its constituent geons, which can themselves be recognized from any viewpoint.


 Top
Abstract
Previous | Next
Table of contents
Full textFull text
Download PDFDownload PDF
Send to a friendSend to a friend
Save this linkSave this link

Open Innovation Challenges

naturejobs

Figures & Tables
Supplementary info
Export citation
natureproducts

Search buyers guide:

 
ADVERTISEMENT
 
Nature Neuroscience
ISSN: 1097-6256
EISSN: 1546-1726
Journal home | Advance online publication | Current issue | Archive | Press releases | Supplements | Focuses | For authors | Online submission | Permissions | For referees | Free online issue | About the journal | Contact the journal | Subscribe | Advertising | work@npg | naturereprints | About this site | For librarians
Nature Publishing Group, publisher of Nature, and other science journals and reference works©1998 Nature Publishing Group | Privacy policy