Hyperspectral Image Feature Extraction Based on Multilinear Sparse Component Analysis

Feature extraction generates a low-dimensional representation of high-dimensional sample data, which retaining most of the information regarding the spatial feature and the spectral feature. A new hyperspectral image tensor feature extraction method based on Multilinear Sparse Principal Component Analysis is proposed in this paper. Experimental results indicate that the proposed method can maintain the spatial-spectral information and discriminating information, which has better classification accuracy than other algorithms when it is applied to the classification images, and the overall classification accuracies reach 96.36 and 95.00%, respectively.