摘要： As a widely used classi?er, sparse representation classi?cation (SRC) has shown its good performance for hyperspectral image classi?cation. Recent works have highlighted that it is the collaborative representation mechanism under SRC that makes SRC a highly effective technique for classi?cation purposes. If the dimensionality and the discrimination capacity of a test pixel is high, other norms (e.g., (cid:96)2-norm) can be used to regularize the coding coef?cients, except for the sparsity (cid:96)1-norm. In this paper, we show that in the kernel space the nonnegative constraint can also play the same role, and thus suggest the investigation of kernel fully constrained least squares (KFCLS) for hyperspectral image classi?cation. Furthermore, in order to improve the classi?cation performance of KFCLS by incorporating spatial-spectral information, we investigate two kinds of spatial-spectral methods using two regularization strategies: (1) the coef?cient-level regularization strategy, and (2) the class-level regularization strategy. Experimental results conducted on four real hyperspectral images demonstrate the effectiveness of the proposed KFCLS, and show which way to incorporate spatial-spectral information ef?ciently in the regularization framework.