L1-graph semisupervised learning for hyperspectral image classification

Recently, research in semisupervised learning (SSL) based on sparse representation has shown huge potential for many classification tasks. In this paper, we address a hyperspectral image classification by integrating L1-graph and SSL. We propose a semisupervised classification method with L1-graph which has more attractive merits than traditional graph method, such as parameter free, sparsity and robustness. Our method firstly obtains the graph weights by solving a L1 optimization problem, and then generates a way of SSL with the L1-graph weights to deal with classification of hyperspectral images. The experiments are designed to cope with challenging real hyperspectral image classification task with a few labeled samples. The experimental results demonstrate the effectiveness of the L1-graph semisupervised method.