AN ℓ1/2 regularized low-rank representation for hyperspectral imagery classification

Hundreds of narrow contiguous spectral bands collected by a hyperspectral sensor has provided the opportunity to identify the various materials present on the surface. 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, by decomposing each pixel and the spatial neighborhood into a low-rank form, the spatial information can be efficiently integrated into the spectral signatures. Meanwhile, in order to describe the low-rank structure of the decomposed data more precisely, an ℓ_1/2 norm regularization is introduced and a discrete algorithm is proposed to solve the combined optimization problem. Experimental results on real hyperspectral data have demonstrated the effectiveness and versatility of the proposed spatial information-fused approach for hyperspectral imagery classification.