Share Email Print
cover

Proceedings Paper

Learning object shapes from examples
Author(s): Hormoz Shariat
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This paper describes a method for learning the 2-D shapes of the objects from their sample image clips. We view an object as a congregation of a set of component parts with simple shapes. When presented with a sample image clip of an object, our learning system first detects the components of that object and saves the shape descriptions of those components in the object model. Next it determines the geometrical relationships between the components which are also saved in the object model as constraints. Finally, it generates a strategy for recognizing such an object. As we will show, our system can use this automatically extracted information to detect such an object in other scenes, even when the object is partially occluded.

Paper Details

Date Published: 1 December 1991
PDF: 10 pages
Proc. SPIE 1567, Applications of Digital Image Processing XIV, (1 December 1991); doi: 10.1117/12.50815
Show Author Affiliations
Hormoz Shariat, Lockheed Palo Alto Research Labs. (United States)


Published in SPIE Proceedings Vol. 1567:
Applications of Digital Image Processing XIV
Andrew G. Tescher, Editor(s)

© SPIE. Terms of Use
Back to Top