Share Email Print

Proceedings Paper

Comparable performance for classifier trained on real or synthetic IR-images
Author(s): Bruce A. Weber; Joseph A. Penn
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

We report results that demonstrate that an infrared (IR) target classifier, trained on synthetic-images of targets and tested on real-images, can perform as well as a classifier trained on real-images alone. We also demonstrate that the sum of real and synthetic-image databases can be used to train a classifier whose performance exceeds that of classifiers trained on either database alone. After creating a large database of 80,000 synthetic-images two subset databases of 7,000 and 8,000 images were selected and used to train and test a classifier against two comparably sized, sequestered databases of real-images. Synthetic-image selection was accomplished using classifiers trained on real-images from the sequestered real-image databases. The images were chosen if they were correctly identified for both target and target aspect. Results suggest that subsets of synthetic-images can be chosen to selectively train target classifiers for specific locations and operational scenarios; and that it should be possible to train classifiers on synthetic-images that outperform classifiers trained on real-images alone.

Paper Details

Date Published: 22 October 2001
PDF: 11 pages
Proc. SPIE 4379, Automatic Target Recognition XI, (22 October 2001); doi: 10.1117/12.445386
Show Author Affiliations
Bruce A. Weber, Army Research Lab. (United States)
Joseph A. Penn, Army Research Lab. (United States)

Published in SPIE Proceedings Vol. 4379:
Automatic Target Recognition XI
Firooz A. Sadjadi, Editor(s)

© SPIE. Terms of Use
Back to Top