Robust classification of hyperspectral images based on the combination of supervised and unsupervised learning paradigms

In this paper, we propose to improve the classification accuracy of hyperspectral images by fusing the capabilities of the support vector machine (SVM) classifier and the fuzzy C-means (FCM) clustering algorithm. While the former is used to generate a spectral-based classification map, the latter is adopted to provide an ensemble of clustering maps. To reduce the computation complexity, the most representative spectral channels identified by the Markov Fisher Selector (MFS) algorithm are used during the clustering process. Then, these maps are successively labeled via a pairwise relabeling procedure with respect to the SVM-based classification map using voting rules. To generate the final classification result, we propose to aggregate the obtained set of spectro-spatial maps through two different fusion methods based on voting rules and Markov Random Field (MRF) theory.