Markov random field with homogeneous areas priors for hyperspectral image classification

This paper presents a novel method to apply homogeneous areas priors adaptively for hyperspectral image classification. Firstly, support vector machine algorithm is utilized to obtain the posterior probability distributions by training the spectral information of the samples. Then, the homogeneous areas generated from the watershed segmentation results are used as new spatial priors. By using Markov Random Field model, we can integrate the spectral information and spatial information which includes the homogeneous areas priors in a unified framework. Compared with neighborhood-generated Markov random field, the adaptive priors strengthen to enforce the segmentation results in homogeneous areas of the neighborhood belong to the same class. Finally, the maximum a posterior segmentation is computed by min-cut based optimization algorithm.