Quantitative analysis of texture parameter estimation in SAR images

This paper deals with the validation of a previously developed texture model for SAR data as well as its associated parameter estimation algorithm. The mentioned model is named the Anisotropic Gaussian Kernel (AGK) model and allows the description of the possibly nonstationary and anisotropic behaviour of texture on heterogeneous areas of SAR images. The parameter estimation performance is evaluated over simulated data. We also investigate about the validity of our model over experimental data, by means of dissimilarity measures.