Target Discrimination Based on Zernike Moments in High-Resolution SAR Imagery

Target discrimination is the key step of automatic target detection (ATR) in synthetic aperture radar (SAR) images. In this paper, a new algorithm for target discrimination in high resolution SAR image is presented by utilizing Zernike moments as descriptors of shape and intensity characteristics which have linear transformation invariance properties. The input regions of interest (ROIs) are segmented and further subjected to a number of preprocessing stages such as histogram equalization, position and size normalization. Two groups of Zernike moments (shape and intensity characteristic) have been extracted from the preprocessed images. Each group includes 70 moments with different orders and iterations. The chosen moments have been applied to a SVM classifier. The proposed scheme has been tested on the MSTAR database. The Receiver Operational Characteristics (ROC) curve and the performance of proposed scheme using some measured data are analyzed. Experimental results have demonstrated the efficiency of the proposed scheme to ability in target discrimination in SAR imagery.