Classification of hyperspectral image based on principal component analysis and deep learning

Classification is an important way to explore the information in hyperspectral images (HSIs). Deep learning algorithm has been introduced into HSI processing and achieved some preliminary results. Deep belief network (DBN) is a typical deep learning model, which combines the advantages of unsupervised and supervised learning and has a good performance in big data classification. In this paper, taken into account both the spatial information and the spectral characteristics of HSI, a hybrid classification method combined DBN with principal component analysis (PCA) is proposed. Experimental results show that the PCA-DBN method has promising prospect in the HSI classification.