Hyperspectral image classification and application based on relevance vector machine

The relevance vector machine (RVM) is used to process the hyperspectral image in this paper to estimate the classifiers precisely in the high dimensional space with limited training samples. The detail of RVM is firstly discussed based on the sparse Bayesian theory. Then four multi-class strategies are analyzed, including One-vs-All (OAA), One-vs-One (OAO) and two direct multi-class strategies. In the experiments, the multi-class strategies are compared and RVM is further compared with several classical classifiers, including the support vector machine (SVM). The experiments show that two direct multi-class strategies occupy too much memory space with low efficiency. OAA has the highest precision, but is low in efficiency. OAO is the best in efficiency and the precision approximates to OAA. Compared with SVM, RVM is low in precision, but sparser than SVM. The sparse property is important when the test set is large, which makes RVM suitable for classifying the large-scale hyperspectral image.