Multiscale stochastic modelling of SAR image for segmentation

A valid unsupervised and multiscale segmentation of synthetic aperture radar (SAR) imagery is proposed by combining Expectation Maximization with the genetic algorithm (CA-EM). The mixture multiscale autoregressive (MMAR) model is introduced to characterize and exploit the scale-to-scale statistical variations and statistical variations in same scale in SAR imagery due to radar speckle, and the estimation of parameters in MMAR model is given by combining the CA algorithm with EM algorithm. This algorithm is capable of selecting the number of components of the model using the minimum description length (MDL) criterion. Our approach benefits from the properties of Genetic algorithms (GA) and the EM algorithm by combination of both into a single procedure. The population-based stochastic search of the CA explores the search space more thoroughly than the EM method. Therefore, our algorithm enables escaping from local optimal solutions since the algorithm becomes less sensitive to its initialization. Some experiment results are given based on our proposed approach, and compared to that of the EM algorithms. The experiments on the SAR images show that the GA-EM outperforms the EM method.