Share Email Print
cover

Proceedings Paper

Avoiding metric similarity measures in ATR
Author(s): Behrooz Kamgar-Parsi; Behzad Kamgar-Parsi; Judith E. Dayhoff; Anil K. Jain
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

In target recognition in uncontrolled environments the test target may not belong to the prestored targets or target classes. Hence, in such environments the use of a typical classifier which finds the closest class still leaves open the question of whether the test target truly belongs to that class. To decide whether a test target matches a stored target, common approaches calculate a degree of similarity between the two targets using a similarity measure such as Euclidean distance, and make a decision based on whether the distance exceeds a (prespecified) threshold. Based on psychophysical studies, this is very different from, and far inferior to, human capabilities. In this paper we show a new approach where a neural network learns a decision boundary between the confirmation vs. rejection of a match with the help of a human critic. The decision boundary is a multidimensional surface, and models the human similarity measure for the recognition task at hand, thus avoiding metric similarity measures and thresholds. A case study in automatic aircraft recognition is shown. In the absence of sufficient real data, the approach allows us to specifically generate an arbitrarily large number of training exemplars projecting near the classification boundary. The performance of the trained network was comparable to that of a human expert, and far better than a network trained only on the available real data. Furthermore, the result were considerably better than those obtained using a Euclidean discriminator.

Paper Details

Date Published: 17 August 2000
PDF: 7 pages
Proc. SPIE 4050, Automatic Target Recognition X, (17 August 2000); doi: 10.1117/12.395594
Show Author Affiliations
Behrooz Kamgar-Parsi, Naval Research Lab. (United States)
Behzad Kamgar-Parsi, Naval Research Lab. (United States)
Judith E. Dayhoff, Complexity Research Solutions, Inc. (United States)
Anil K. Jain, Michigan State Univ. (United States)


Published in SPIE Proceedings Vol. 4050:
Automatic Target Recognition X
Firooz A. Sadjadi, Editor(s)

© SPIE. Terms of Use
Back to Top