Adaptive complex-amplitude texture classifier that deals with both height and reflectance for interferometric SAR images

We propose an adaptive complex-amplitude texture classifier that takes into consideration height as well as reflection statistics of interferometric s ynthetic aperture radar (SAR) images. The classifier utilizes the phase inf ormation to segment the images. The system consists of a two-stage preproce ssor and a complex-valued SOFM. The preprocessor extracts of complex-valued feature vectors corresponding to height and reflectance statistics of bloc ks in the image. The following SOFM generates a set of templates (reference s) adaptively and classifies a block into one of the classes represented by the templates. Experiment demonstrates that the system segments an interfe rometric SAR image successfully into a lake, a mountain, and so on. The per formance is better than that of a conventional system dealing only with the amplitude information.