Spatial–Spectral Locality-Constrained Low-Rank Representation with Semi-Supervised Hypergraph Learning for Hyperspectral Image Classification

Abstract

In this paper, we propose a novel hyperspectral image classification method based on spatial-spectral locality-constrained low-rank representation (LRR) and semi-supervised hypergraph learning. Specifically, we first represent the hyperspectral data via LRR due to its abilities in both recovering the low-rank structure of high-dimensional observations and dealing with the noises corrupted during imaging. Then, we incorporate a locality constraint based on spatial-spectral similarity into the LRR model to further preserve the spatial information and local manifold structure. Based on LRR features, a semi-supervised hypergraph learning algorithm is designed for final classification to fully exploit the rich information of unlabeled samples. Different from the conventional pair-wise graph model, the hypergraph model can effectively capture high-order relationships among samples. Experiments are conducted on three benchmark hyperspectral datasets, and the results show that the proposed method achieves superior classification performance over other state-of-the-art methods and possesses the robustness to noise.