New automated method for estimating the number of endmembers in hyperspectral images

Knowing the number of endmembers in a hyperspectral image is a prerequisite for almost all the endmember extraction algorithms and plays a key role for the accuracy of the spectral unmixing. Moreover, in case of data compression, it is important to know the number of endmembers in order to define the appropriate signal subspace. In this paper, a new automated method for estimating the number of endmembers in hyperspectral imagery is proposed, without the need of a priori knowledge. The method is based on the intra-band standard deviation values of the transformed components produced by eigen-based decomposition, and uses a fixed threshold -the same regardless the hyperspectral dataset- to define the optimum signal subspace. The effectiveness of the proposed method is shown using synthetic and real data. Comparison with state-of-the-art methods for the estimation of the number of endmembers is also performed.