Man-made object classification in SAR images using Gabor wavelet and neural network classifier

In this paper, a novel descriptive feature extraction method of Gabor wavelet and neural network classifier for classification of Synthetic Aperture Radar (SAR) images is proposed. For this purpose, the Neural Network algorithm includes the user made MATLAB code. The classification process has the following stages (1) Image preprocessing (median filtering, histogram equalization, binarization) (2) Feature extraction using Gabor Wavelet Transform (3) Neural Network classification. The algorithm has been applied for the three classes of military manmade objects (metal objects) in SAR imagery is using MSTAR public release database. Experimental results are presented.