Hyperspectral image classification using an extended Auto-Encoder method

This article proposes a spectral-spatial method for classification of hyperspectral images (HSIs) by modifying traditional Auto-Encoder based on Majorization Minimization (MM) technique. The proposed method consists of suggesting three main modifications. First, to construct weights of Auto-Encoder, similarity angle map(SAM) criterion is used as regularization term. It is useful to extract spectral similarity of initial features. Second, to enhance the classification accuracy, fuzzy mode is used to estimate parameters. These modifications lead to create an extended Auto-Encoder based on MM (EAEMM). Third, to improve the performance of Auto Encoder, multi-scale features (MSF) are extracted. In comparison with some of the state-of-the-art methods, the experimental results obtained using the proposed method (MSF-EAEMM) show that it significantly improves the classification accuracy of HSI classification.

Automated summary

This article proposes a spectral-spatial method for classification of hyperspectral images by modifying traditional Auto-Encoder based on Majorization Minimization technique. The proposed method suggests three main modifications to improve classification accuracy, including using SAM criterion for constructing weights, fuzzy mode for estimating parameters, and extracting multi-scale features. Experimental results show significant improvement in HSI classification accuracy compared to state-of-the-art methods.