Spectral–spatial hyperspectral image ensemble classification via joint sparse representation. (November 2016)

• Record Type: Journal Article
• Authors: Zhang, Erlei; Zhang, Xiangrong; Jiao, Licheng; Li, Lin; Hou, Biao
• Is Part Of: Pattern recognition. Volume 59(2016:Nov.)
• Page Start: 42
• Page End: 54
• Publication Date: 2016-11
• Subjects: Classification -- Ensemble learning -- Hyperspectral imagery -- Joint sparse recovery -- Spatial correlation; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2016.01.033
• Languages: English
• ISSNs: 0031-3203

Abstract

Abstract: Ensemble learning can improve the performance of classification by integrating a set of classifiers, and shows significant potential benefits to the classification of hyperspectral image. However, the ensemble strategy remarkably influences the classification results, which include determining the minimum number of classifiers and assigning advisable weights associated with each classifier. In this paper, we present a novel sparse ensemble learning method with spectral–spatial knowledge for hyperspectral image classification. It considers the ensemble strategy under sparse recovery framework, where the solved non-zero coefficients reveal the importance of the selected classifier, from which a compact and effective ensemble learning system can be derived. Moreover, the spatial information is incorporated into the classification to develop a spectral–spatial joint sparse representation based ensemble learning algorithm for more accurate classification of hyperspectral images. Experimental results on several real hyperspectral images show that the proposed sparse ensemble system can achieve better performance than traditional ensemble learning methods using all classifiers, and it largely improves the efficiency in testing phase. Highlights: Ensemble learning problems are considered as sparse reconstruction problems. Incorporate the contextual neighborhood knowledge during the learning stage. Complete the selection of classifiers subset and obtain weights in one step. The new ensemble system using fewer classifiers not only yields better performance but also reduces computational burden in testing phase.