Integration of Spatial and Spectral Information by Means of Sparse Representation-Based Classification for Hyperspectral Imagery

Recently, sparse representation-based classification (SRC), which assigns a test sample to the class with minimum representation error via a sparse linear combination of all the training samples, has successfully been applied to hyperspectral imagery. Meanwhile, spatial information, that means the adjacent pixels belong to the same class with a high probability, is a valuable complement to the spectral information. In this paper, we have presented a new spatial-neighborhood-integrated SRC method, abbreviated as SN-SRC, to jointly consider the spectral and spatial neighborhood information of each pixel to explore the spectral and spatial coherence by the SRC method. Experimental results have shown that the proposed SN-SRC approach could achieve better performance than the other state-of-the-art methods, especially with limited training samples.