Share Email Print
cover

Optical Engineering

Target classification via support vector machines
Author(s): Robert E. Karlsen; David J. Gorsich; Grant R. Gerhart
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

The area of automatic target classification has been a difficult problem for many years. Many approaches involve extracting information from the imagery through a variety of statistical filtering and sampling techniques, resulting in a reduced dimension feature vector that is the input for a learning algorithm. We introduce the support vector machine (SVM) algorithm, which is a wide margin classifier that can provide reasonable results for sparse data sets and whose training speed can be nearly independent of feature vector size. Therefore, we can avoid the feature extraction step and process the images directly. The SVM algorithm has the additional features that there are few parameters to adjust and the solutions are unique for a given training set. We apply SVM to a vehicle classification problem and compare the results to standard neural network approaches. We find that the SVM algorithm gives equivalent or higher correct classification results compared to neural networks.

Paper Details

Date Published: 1 March 2000
PDF: 8 pages
Opt. Eng. 39(3) doi: 10.1117/1.602417
Published in: Optical Engineering Volume 39, Issue 3
Show Author Affiliations
Robert E. Karlsen, U.S. Army Tank-Automotive Research Development and Engineering Ctr. (United States)
David J. Gorsich, U.S. Army Tank-Automotive Research Development and Engineering Ctr. (United States)
Grant R. Gerhart, U.S. Army Tank-Automotive Research Development and Engineering Ctr. (United States)


© SPIE. Terms of Use
Back to Top