Hyperspectral image reconstruction by deep convolutional neural network for classification. (March 2017)

• Record Type: Journal Article
• Authors: Li, Yunsong; Xie, Weiying; Li, Huaqing
• Is Part Of: Pattern recognition. Volume 63(2017:Mar.)
• Page Start: 371
• Page End: 383
• Publication Date: 2017-03
• Subjects: Hyperspectral imagery -- Deep convolutional neural network -- Extreme learning machine -- Reconstruction -- Band selection -- Pattern classification; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2016.10.019
• Languages: English
• ISSNs: 0031-3203

Abstract

Abstract: Spatial features of hyperspectral imagery (HSI) have gained an increasing attention in the latest years. Considering deep convolutional neural network (CNN) can extract a hierarchy of increasingly spatial features, this paper proposes an HSI reconstruction model based on deep CNN to enhance spatial features. The framework proposes a new spatial features-based strategy for band selection to define training label with rich information for the first time. Then, hyperspectral data is trained by deep CNN to build a model with optimized parameters which is suitable for HSI reconstruction. Finally, the reconstructed image is classified by the efficient extreme learning machine (ELM) with a very simple structure. Experimental results indicate that framework built based on CNN and ELM provides competitive performance with small number of training samples. Specifically, by using the reconstructed image, the average accuracy of ELM can be improved as high as 30.04%, while performs tens to hundreds of times faster than those state-of-the-art classifiers. Highlights: The feature enhancement step is introduced in the proposed HRCNN model because that the HSI is contaminated with noise. A new band selection method based on spatial features is proposed in this training model. A new exploration to combine CNN with ELM for HSI classification under a small training set is achieved.