Hyperspectral Image Classification Based on Dimension Reduction Combination and Rotation SVM Ensemble Learning

摘要

A rotation SVM ensemble learning method based on dimension reduction combination is proposed aiming at the problem of dimensionality disaster and low classification accuracy of hyperspectral remote sensing images. PCA algorithm is used to reduce dimension firstly. This method can not only eliminate data redundancy and retain the main information but also realize non-singularity of intra-class distance matrix that LDA required. Then LDA method is used to reduce dimension based on projection secondly. The twice dimension reduction produce the minimum intra-class distance, the maximum inter-class distance and the best discrimination of samples. Then, the sample after twice dimension reduction is classified by Rotation SVM ensemble learning algorithm. SVM is use to be base classifier because of its high classification accuracy. In order to enhance the samples diversity of ensemble classifiers, rotation matrix is constructed firstly, and then SVM classifier is trained on each rotation matrix. Above steps are performed repeatedly, classification result is produced by voting method finally. Experimental results based on Indian Pines hyperspectral images show that the reduction dimension effect and classification accuracy of the proposed method are better than other classification methods.