Share Email Print

Proceedings Paper

Classifier combination and feature selection methods for polarimetric SAR classification
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Training classifiers individually, and then fusing their results, has the potential to improve classification accuracy; often, dramatic improvements are realized. In this paper we examine how training classifiers using multiple polarimetric features such as the Cloude-Pottier decomposition, even and odd bounce and the Polarimetric Whitening filter and then fusing their results affects performance of ship classification. We explore and compare two currently competing technologies of classifier bagging and classifier boosting for classifier fusion and introduce a new approach which conducts a search through solution space to configure an optimal classifier given a library of classifiers and features. A related and important facet of this work is feature selection and feature reduction methods. We explore how the selection of different features affects classification performance. We also explore estimates of the classifier error and provide estimates for noise bounds on the data and compare performance of the different methods compared to the noise present in data.

Paper Details

Date Published: 9 April 2007
PDF: 12 pages
Proc. SPIE 6571, Multisensor, Multisource Information Fusion: Architectures, Algorithms, and Applications 2007, 65710B (9 April 2007); doi: 10.1117/12.719407
Show Author Affiliations
G. Gigli, A.U.G. Signals Ltd. (Canada)
R. Sabry, Defence Research and Development Canada (Canada)
G. Lampropoulos, A.U.G. Signals Ltd. (Canada)

Published in SPIE Proceedings Vol. 6571:
Multisensor, Multisource Information Fusion: Architectures, Algorithms, and Applications 2007
Belur V. Dasarathy, Editor(s)

© SPIE. Terms of Use
Back to Top