Unsupervised subspace linear spectral mixture analysis for hyperspectral images

In this paper, an unsupervised subspace linear spectral unmixing algorithm for hyperspectral data is investigated, which includes two key techniques: subspace minimum noise fraction transformation (SMNFT) and independent component analysis (ICA). The SMNFT is used to reduce noise, remove correlation between neighboring bands and determine intrinsic dimensionality of hyperspectral data. Then the ICA is applied to unmix hyperspectral images and obtain independent endmembers. The main merits of the proposed algorithm are that it can fast unsupervisedly separate useful and independent endmembers resident in hyperspectral images. The experimental results demonstrate that this algorithm can effectively identify independent endmembers. Meanwhile, the results show high computational efficiency of the algorithm. The time consumed by the SMNFT is merely one fifth of the traditional minimum noise fraction transformation.