Feature-based target recognition with Bayesian inference

The problem of target classification with high-resolution fully polarimetric, synthetic aperture radar (SAR) imagery is considered. The paper summarizes our recent work in SAR target recognition using a feature-based Bayesian inference approach. The approach works on the selected features. Features are chosen such that the separabilities of the original data are well maintained for later classification. Once the original data is mapped into feature space, the conditional probability distributions of features given the target are estimated statistically, which are then used to calculate the probabilities that a target belongs to one of the given classes based on the observed features. The target is assigned to the class with the highest probability. A comparison between the above technique and the traditional statistical approaches such as nearest mean and Fisher pairwise is illustrated based upon performance on a fully polarimetric ISAR (inverse SAR) image data set.