Classifiction for hyperspectral imagery based on nonlocal weighted joint sparsity model

A nonlocal weighted joint sparse representation classification method for hyperspectral image is proposed in this paper. A discriminated contributions based on nonlocal spatial structure information are utilized in the joint sparsity model framework. The proposed algorithm is tested on two hyperspectral images. Experimental results suggest that the proposed algorithm shows superior performance over other sparsity-based algorithms and the classical hyperspectral classifier SVM.