Polarimetric SAR image segmentation with hidden Markov random field models

A segmentation algorithm based on a hidden Markov random field model is applied to a (HH, VV) polarimetric SAR (synthetic aperture radar) image pair. The segmentations, assuming two classes, of the HH and VV images separately are shown, after 100 stages of stochastic relaxation. The results agree with the visual perception of the images. The segmentation, assuming two classes, of HH and VV images jointly is also shown, again after 100 stages.<>