Two-dimensional PCA for SAR automatic target recognition

Author

Lu, XiaoGuang ; Han, Ping ; Wu, Renbiao

Author_Institution

Civil Aviation Univ. of China, Tianjin

fYear

2007

fDate

5-9 Nov. 2007

Firstpage

513

Lastpage

516

Abstract

In this paper, a new technique for synthetic aperture radar (SAR) automatic target recognition (ATR) is developed, which is builded upon two-dimensional principle component analysis (2DPCA). First, 2DPCA is applied to extract features in frequency domain, which is based on image matrix directly. Then support vector machine (SVM) is used for classification. Experimental results on MSTAR dataset show that the 2DPCA method both gives higher recognition rate, and are computationally more efficient than PCA.

Keywords

feature extraction; image classification; principal component analysis; radar imaging; radar target recognition; support vector machines; synthetic aperture radar; 2DPCA; MSTAR dataset; SAR automatic target recognition; feature extraction; frequency domain; image classification; image matrix; support vector machine; synthetic aperture radar; Covariance matrix; Eigenvalues and eigenfunctions; Feature extraction; Image analysis; Principal component analysis; Radar signal processing; Support vector machine classification; Support vector machines; Synthetic aperture radar; Target recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Synthetic Aperture Radar, 2007. APSAR 2007. 1st Asian and Pacific Conference on

Conference_Location

Huangshan

Print_ISBN

978-1-4244-1188-7

Electronic_ISBN

978-1-4244-1188-7

Type

conf

DOI

10.1109/APSAR.2007.4418662

Filename

4418662