SAR Images Feature Extraction and Target Recognition Based on ICA and SVM

This paper presents a new method for Synthetic Aperture Radar(SAR) images feature extraction and target recognition using independent component analysis and support vector machine. Low-frequency sub-band image is obtained by wavelet decomposition of a SAR image. Independent Component Analysis(ICA) is used for extracting feature vectors from the low-frequency sub-band image as the feature of the target. Support Vector Machine(SVM) is used to perform target recognition. The method is used for recognizing three-class targets in MSTAR database and the recognition rate arrives at 96.92%. Experimental result shows that the method is an effective method for SAR images feature extraction and target recognition.