Hyperspectral image classification method based on semantic filtering and ensemble learning

•A semantic-based edge preserving filtering SEPF is proposed.•An effective weight coefficient is introduced to measure the quality of features of different scales, so that more qualified features have higher confidence.•Ensemble learning effectively combines multi-scale features, and the weighted voting strategy enhances the information-rich features.•The proposed method is robust and can achieve high classification accuracy when there are only a few labeled samples are available. The imbalance between limited training samples and extreme high spectral dimensions is a challenge for hyperspectral image classification. To significantly improve the classification of hyperspectral images in the case of small samples, we proposed a novel hyperspectral image classification method based on semantic filtering and ensemble learning. Semantic filtering synergistically combines the efficiency of the recursive filter and the effectiveness of the recent edge detector for scale-aware edge-preserving filtering, which can efficiently extract subjectively meaningful structures from natural scenes containing multiple-scale objects. Ensemble learning is used to fuse multi-scale features and to enhance the information-rich features. Experiments on three data sets prove that both semantic information and ensemble learning can improve classification accuracy, and their combination obtained the state-of-the-art performance.