Constrained Nonnegative Matrix Factorization Used for Spectral Unmixing

The mixels in the hyperspectral images directly influence the accuracy of target recognition. The ICE algorithm doesn't extract the endmembers based on the hypothesis of the pure pixels' existence, and gets good performance in the spectral unmixing application. After analyzing the theory of the the ICE algorithm and nonnegative matrix factorization, the method of hyperspectral image unmixing via endmembers' sum of squared distance constrained nonnegative matrix factorization was presented. Experimental results demonstrated that the proposed scheme for decomposition of mixels outperforms the ICE algorithm..