Share Email Print
cover

Proceedings Paper

Detection performance prediction on IR images assisted by evolutionary learning
Author(s): Liviu I. Voicu; Ronald Patton; Harley R. Myler
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Background clutter characterization in IR imagery has become an actively researched field and several clutter models have been reported. These models attempt to evaluate the target detection/recognition probabilities that are characteristic to a certain scene when specific target and human visual perception features are known. The prior knowledge assumed and required by these models is a severe limitation. Furthermore, the attempt to model subjective and intricate mechanisms such as human perception with simple mathematical formulae is controversial. In this paper, we introduce the idea of adaptive models that are dynamically derived from a set of examples by a supervised evolutionary learning scheme. A set of characteristic scene and target features with a demonstrated influence on the human visual perception mechanism is first extracted from the original images. Then, the correlation between these features and the results obtained by visual observer tests on the same set of images are captured into a model by the learning scheme. The effectiveness of the adaptive modeling principle is discussed in the final part of the paper.

Paper Details

Date Published: 14 July 1999
PDF: 11 pages
Proc. SPIE 3699, Targets and Backgrounds: Characterization and Representation V, (14 July 1999); doi: 10.1117/12.352956
Show Author Affiliations
Liviu I. Voicu, I-Math Associates, Inc. (United States)
Ronald Patton, I-Math Associates, Inc. (United States)
Harley R. Myler, I-Math Associates, Inc. (United States)


Published in SPIE Proceedings Vol. 3699:
Targets and Backgrounds: Characterization and Representation V
Wendell R. Watkins; Dieter Clement; William R. Reynolds, Editor(s)

© SPIE. Terms of Use
Back to Top