Genetic-Based EM Algorithm for Classification of SAR Imagery

A valid unsupervised and multiscale classification method of synthetic aperture radar (SAR) imagery is proposed based on the Expectation Maximization and the genetic algorithm (GA-EM). This algorithm is capable of selecting the number of classification of SAR image using the Bayesian information criterion (BIC) for Gaussian mixture model. 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 GA 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 other algorithms. The experiments on the SAR images show that the method based on the GA-EM outperforms the other method.