Latent Low-Rank Projection Learning with Graph Regularization for Feature Extraction of Hyperspectral Images

Due to the great benefit of rich spectral information, hyperspectral images (HSIs) have been successfully applied in many fields. However, some problems of concern also limit their further applications, such as high dimension and expensive labeling. To address these issues, an unsupervised latent low-rank projection learning with graph regularization (LatLRPL) method is presented for feature extraction and classification of HSIs in this paper, in which discriminative features can be extracted from the view of latent space by decomposing the latent low-rank matrix into two different matrices, also benefiting from the preservation of intrinsic subspace structures by the graph regularization. Different from the graph embedding-based methods that need two phases to obtain the low-dimensional projections, one step is enough for LatLRPL by constructing the integrated projection learning model, reducing the complexity and simultaneously improving the robustness. To improve the performance, a simple but effective strategy is exploited by conducting the local weighted average on the pixels in a sliding window for HSIs. Experiments on the Indian Pines and Pavia University datasets demonstrate the superiority of the proposed LatLRPL method.

Automated summary

This paper proposes an unsupervised latent low-rank projection learning with graph regularization method for feature extraction and classification of hyperspectral images. By decomposing the latent low-rank matrix and applying graph regularization, discriminative features can be extracted and intrinsic subspace structures can be preserved, leading to improved performance. The use of local weighted average in a sliding window is also effective in further enhancing the performance.