Feature Extraction and Classification of ISAR Images Based on SVM

Konferenz: EUSAR 2006 - 6th European Conference on Synthetic Aperture Radar
16.05.2006 - 18.05.2006 in Dresden, Germany

Tagungsband: EUSAR 2006

Seiten: 4Sprache: EnglischTyp: PDF

Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt

Autoren:
Su, Fulin; Li, Shaobin; Zhang, Ye (Harbin Institute of Technology, P. R. China)

Inhalt:
In this paper, an auto-target-recognition method based on ISAR image was presented. Three types of features were implemented, namely the Fourier coefficients, the wavelet coefficients and some shape features of the ISAR image. Also, three kinds of classifiers: nearest-neighbour, BP neural network and SVM, are considered. Experimental results showed that the Fourier coefficients with some shape features and the SVM classifier had the best discrimination and the classifcaltion precision can reach to more than 94%.