Spectral-spatial classification based on subspace support vector machine and Markov random field

Haoyang Yu, Lianru Gao, Jun Li, Bing Zhang

Abstract: This paper proposes a new supervised classification method for hyperspectral images combining the spectral and spatial information. The main contribution is presented by combining subspace-based support vector machine (SVMsub) and Markov random field (MRF). A SVM classifier integrated with a subspace projection is first used to model the posterior distributions of the classes from the spectral information. Then, the spatial information is modeled by a multilevel MRF. Finally, the maximum posterior probability classification is computed via the α-Expansion graph-cut-based optimization algorithm. The proposed method, abbreviated as SVMsub-MRF, is validated using a real typical hyperspectral data set. The results indicate that the proposed method exhibits better performance on accuracy and computational cost compared to other related classical hyperspectral image classification methods.