Share Email Print

Proceedings Paper

Automatic building and supervised discrimination learning of appearancemodels of 3D objects
Author(s): Richard L. Delanoy; Jacques G. Verly; Dan E. Dudgeon
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Mechanisms for automatically building and refining appearance models (AMs) of 3-D objects are presented. AMs encode allowed ranges of values of target characteristics called attributes. Allowed values for each attribute of arbitrarily defined parts of a modeled object are determined by statistical analysis of an example set of known targets. Once models are built, the system learns which attributes are discriminating (important to making a correct identification) from mistakes made on a set of training data. In discrimination learning, a weight associated with an attribute is increased or decreased whenever a test for an attribute denies or supports an incorrect object identification, respectively. A consistently decreasing weight eventually results in the essential elimination of the associated attribute from the AM. We illustrate and evaluate this approach in the context of our work in automatic target recognition (ATR).

Paper Details

Date Published: 1 March 1992
PDF: 12 pages
Proc. SPIE 1708, Applications of Artificial Intelligence X: Machine Vision and Robotics, (1 March 1992); doi: 10.1117/12.58600
Show Author Affiliations
Richard L. Delanoy, Lincoln Lab./MIT (United States)
Jacques G. Verly, Lincoln Lab./MIT (United States)
Dan E. Dudgeon, Lincoln Lab./MIT (United States)

Published in SPIE Proceedings Vol. 1708:
Applications of Artificial Intelligence X: Machine Vision and Robotics
Kevin W. Bowyer, Editor(s)

© SPIE. Terms of Use
Back to Top