Hyperspectral Image Classification Based on Multiple Features and an Improved Autoencoder

In this study, we propose a hyperspectral image classification algorithm based on multiple features and the improved stacked sparse autoencoder network to solve the problems of insufficient feature utilization and less training samples. The low-dimensional data structures of the hyperspectral images can be obtained using manifold learning, and the local binary pattern (LEP) features with spatial information and extended multi-attribute profiles (EMAP) features can be extracted from the hyperspectral images. Further, Active learning is used to query and label highly characteristic unlabeled samples. Then, the samples fusing space spectrum joint information arc used to train the stacked active sparse autoencoder neural network; these samples arc subsequently classified using the Softmax classifier. The overall classification accuracy of the Indian pines dataset was 98.14%, whereas the overall classification accuracy of the Pavia U dataset was 97. 24 %. The experimental results prove that the proposed algorithm has a high classification accuracy and can appropriately classify the boundary points.