Share Email Print
cover

Proceedings Paper

Classifiability Of Infrared Target Signatures
Author(s): A. B. Lucero; J. W. Bair; R. R. Ramroth; C. T. McAbee
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The issue of infrared target imagery classifiability is investigated. Features that provide class discrimination information are automatically discovered and used to construct n-ary decision tree classifiers. Independent test data are classified and resulting performance reported. The importance of a priori information available in a realistic military scenario is assessed. Other factors affecting performance are also assessed. Probability of correct classification for a four-class problem ranges between 0.33 and 1.00 for various subsets of a standardized data base.

Paper Details

Date Published: 30 June 1989
PDF: 9 pages
Proc. SPIE 1050, Infrared Systems and Components III, (30 June 1989); doi: 10.1117/12.951430
Show Author Affiliations
A. B. Lucero, Northrop (United States)
J. W. Bair, Northrop (United States)
R. R. Ramroth, Northrop (United States)
C. T. McAbee, Northrop (United States)


Published in SPIE Proceedings Vol. 1050:
Infrared Systems and Components III
Robert L. Caswell, Editor(s)

© SPIE. Terms of Use
Back to Top