Analysis of PC number selection in SAR ATR

Author

Wang, Ying ; Han, Ping ; Wu, Renbiao

Author_Institution

Civil Aviation Univ. of China, Tianjin

fYear

2007

fDate

5-9 Nov. 2007

Firstpage

521

Lastpage

524

Abstract

The effect of PC (principal component) number upon SAR ATR (synthetic aperture radar automatic target recognition) performance based on PCA (principal component analysis) is analyzed. First, PCA features are extracted with different PC number, and then SVM is used to classify. Experimental results based on MSTAR data sets show that the performance is optimized when the accumulative contribution rate of the selected PC is 70%. Compared with the common selected method of PC number, the new selection method improves recognition performance and also reduces computational complexity.

Keywords

feature extraction; principal component analysis; radar target recognition; support vector machines; synthetic aperture radar; PCA feature extraction; SAR ATR; SVM; principal component analysis; principal component number selection; support vector machine; synthetic aperture radar automatic target recognition; Computational complexity; Eigenvalues and eigenfunctions; Feature extraction; Performance analysis; Principal component analysis; Signal analysis; 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.2007.4418664

Filename

4418664