Share Email Print

Proceedings Paper

Distance metric learning for ship classification in SAR images
Author(s): Yongjie Xu; Haitao Lang; Xiaopeng Chai; Li Ma
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Synthetic aperture radar (SAR) ship image classification is of great significance in the field of marine ship monitoring. Extracting effective feature representation and constructing suitable classifier can fundamentally improve the accuracy of ship classification. At present, using distance metric learning (DML) algorithm to learn effective distance metrics for classifiers has been widely used in information retrieval and face recognition, but its ability to implement SAR ship image classification is still unknown. In this paper, we show the performance of 4 feature representations and 20 DML algorithms in SAR ship classification. Experimental results show that extracting effective feature representation is essential, and the DML algorithm has the ability to learn better distance metrics.

Paper Details

Date Published: 9 October 2018
PDF: 11 pages
Proc. SPIE 10789, Image and Signal Processing for Remote Sensing XXIV, 107891C (9 October 2018); doi: 10.1117/12.2324954
Show Author Affiliations
Yongjie Xu, Beijing Univ. of Chemical Technology (China)
Haitao Lang, Beijing Univ. of Chemical Technology (China)
Xiaopeng Chai, Beijing Univ. of Chemical Technology (China)
Li Ma, China Three Gorges Corp. (China)

Published in SPIE Proceedings Vol. 10789:
Image and Signal Processing for Remote Sensing XXIV
Lorenzo Bruzzone; Francesca Bovolo, Editor(s)

© SPIE. Terms of Use
Back to Top