27 March 1987 Indexing Shapes for Recognition
Author Affiliations +
Proceedings Volume 0726, Intelligent Robots and Computer Vision V; (1987) https://doi.org/10.1117/12.937709
Event: Cambridge Symposium_Intelligent Robotics Systems, 1986, Cambridge, MA, United States
Abstract
The visual features most important for object recognition are those having to do with the shape of an object. In one approach to recognition The image is decomposed an image into a set of relatively simple shapes (parts) and predicates that describe these parts and the relationships between them. Recognition is a matter of matching this parts-relations description to some parts-relations model in a large database of models. Matching is computationally intensive; unless the parts-relations representation is organized for efficient indexing, recognition times get intractably long. We review general requirements for such a representation as proposed by Marr and Nishihara[1]. Their prescription leaves open general questions that must be answered in any particular implementation. We offer some solutions for a simple domain of 2-D sticklike objects and point out some aspects of the implementa-tion that might be useful for shape indexing in other domains.
© (1987) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Gene R. Gindi, Gene R. Gindi, Donald H. Delorie, Donald H. Delorie, } "Indexing Shapes for Recognition", Proc. SPIE 0726, Intelligent Robots and Computer Vision V, (27 March 1987); doi: 10.1117/12.937709; https://doi.org/10.1117/12.937709
PROCEEDINGS
8 PAGES


SHARE
RELATED CONTENT

Model-Based Object Recognition Using The Connection Machine
Proceedings of SPIE (February 18 1988)
Three-Dimensional Object Recognition Using Range Data
Proceedings of SPIE (March 26 1989)
Robust regression in computer vision
Proceedings of SPIE (January 31 1991)
Two-Dimensional Shape Recognition Using Redundant Hashing
Proceedings of SPIE (February 28 1990)
Knowledge-based system for analysis of aerial images
Proceedings of SPIE (January 31 1991)

Back to Top