Segmented and non-segmented stacked denoising autoencoder for hyperspectral band reduction

Abstract Hyperspectral image (HSI) analysis often requires selecting the most informative bands instead of processing the whole data without losing the key information. Existing band reduction (BR) methods have the capability to reveal the nonlinear properties exhibited in the data but at the expense of losing its original representation. To cope with the said issue, an unsupervised non-linear segmented and non-segmented stacked denoising autoencoder (UDAE)-based BR method is proposed. Our aim is to find an optimal mapping and construct a lower-dimensional space that has a similar structure to the original data with least reconstruction error. The proposed method first confronts the original HS data into smaller regions in the spatial domain and then each region is processed by UDAE individually. This results in reduced complexity and improved efficiency of BR for classification. Our experiments on publicly available HS datasets with various types of classifiers demonstrate the effectiveness of UDAE method which equates favorably with other state-of-the-art dimensionality reduction and BR methods.