A spectral-spatial SVM-based multi-layer learning algorithm for hyperspectral image classification. Issue 3 (4th March 2018)

• Record Type: Journal Article
• Authors: Zhao, Chunhui; Liu, Wu; Xu, Yan; Wen, Jinhuan
• Is Part Of: Remote sensing letters. Volume 9:Issue 3(2018)
• Page Start: 218
• Page End: 227
• Publication Date: 2018-03-04
• Subjects: Remote sensing -- Periodicals; Remote sensing; Periodicals; 621.3678
• DOI: 10.1080/2150704X.2017.1415475
• Languages: English
• ISSNs: 2150-704X

Abstract

ABSTRACT: Conventional Markov random field (MRF) or Graph cut (GC) based support vector machine (SVM) methods for hyperspectral image (HSI) classification use MRF or GC to adjust spectral-based SVM results to increase the spatial consistency in an unsupervised way, thus, the pixels on the border and small-sized regions may be misclassified. In this letter, we propose a new framework of spectral-spatial SVM based multi-layer learning algorithm (SSMLL) for HSI classification. In the first layer of SSMLL, the spectral-based SVM is adopted to process the original HSI datasets; the nonlinear mapping is used to scale the first layer output and enhance the nonlinear structure in the second layer; in the last layer, the spatial information is incorporated into the SVM to obtain the final classification results in a supervised way. Experimental results show that the proposed SSMLL framework provides superior classification accuracy when compared to several state-of-the-art spectral-spatial SVM-based algorithms.