Spectral-Spatial Hyperspectral Image Classification Based on Multiple Views and Multigraphs Fusion With Few Labeled Samples

The issue of limited labeled samples is still grave in hyperspectral image classification. Semisupervised learning (SSL) utilizing both labeled and unlabeled samples promotes a solution to this issue. However, it has been found that the performance of a single SSL is frail when the labeled samples are limited. To tackle this problem, we propose 3-D-Gabor and multiple graphs semisupervised framework (3DG-MGSF). The whole framework is tripartite, including multiviews generation and selection, multiple graphs-based label propagation (LP), and double layers classification fusion process. Specifically, a number of 3-D-Gabor filters with various directions and frequencies are employed to generate multiple views. Afterward, a double multiviews selection procedure is applied to ensure the sufficiency and diversity of multiple views. Subsequently, it is time for the multiple graphs-based LP to be put on its pump. Moreover, spatial and spectral classifications are combined based on the weighted re-fusion algorithm to obtain the final classification. Experimental results illustrate numerically and visually the significantly superior performance of the proposed algorithm compared with four state-of-the-art algorithms with few labeled samples.