Tensor-based multigraph structure preserving embedding for dimensionality reduction of hyperspectral images

An important solution to the curse of dimensionality problem in large-volume, multi-band hyperspectral data is to perform the dimensionality reduction (DR) through graph embedding (GE) techniques. In this paper, a novel DR method called tensor-based multigraph structure preserving embedding (TMSPE) is proposed for HSI classification. At first, TMSPE defines a multi-graph structure with pixel-sharing weights, which can integrate the spatial-spectral information within the tensor samples. Then, it selects effective neighbor points for multigraph construction based on the probability distribution of different samples, which ensures than all nodes in the multigraph structure have correct connection relationships. Finally, the spatial coordinate relationships between pixels are introduced to adjusts the connection weights between different pixels adaptively, which can enhance the effectiveness of manifold reconstruction for HSI data. The performance of TMSPE is evaluated on PaviaU dataset, and experimental comparisons with several classical algorithms demonstrate the superiority of the proposed TMSPE algorithm in terms of classification accuracy.