Classification of SAR images using morphological texture features

This paper presents applications of Synthetic Aperture Radar (SAR) image cl assification using morphological texture features. The texture features are based on morphological residues of opening and closing by reconstruction. It is shown that this set of features shows high 'robustness' to speckle pe rturbation in SAR images compared with those derived from traditional morph ological residues. An algorithm based on estimating the divergence between and within classes was constructed in order to search for a discriminating feature subset. Higher classification accuracy was obtained by the optimize d feature subset than by using other feature subsets derived from some well known texture characterization approaches. The classification accuracy was continuously improved by the introduction of post-processing filtering.