APSIPA Transactions on Signal and Information Processing > Vol 9 > Issue 1

Multiple feature regularized kernel for hyperspectral imagery classification

Xu Yan, Mississippi State University, USA, Peng Jiangtao, Hubei University, China, pengjt1982@126.com , Du Qian, Mississippi State University, USA
 
Suggested Citation
Xu Yan, Peng Jiangtao and Du Qian (2020), "Multiple feature regularized kernel for hyperspectral imagery classification", APSIPA Transactions on Signal and Information Processing: Vol. 9: No. 1, e10. http://dx.doi.org/10.1017/ATSIP.2020.8

Publication Date: 26 Mar 2020
© 2020 Xu Yan, Peng Jiangtao and Du Qian
 
Subjects
 
Keywords
Hyperspectral imageClassificationFeature fusion
 

Share

Open Access

This is published under the terms of the Creative Commons Attribution licence.

Downloaded: 1769 times

In this article:
I. INTRODUCTION 
II. REGULARIZED KERNEL 
III. PROPOSED FRAMEWORK 
IV. EXPERIMENTAL RESULTS 
V. CONCLUSIONS 

Abstract

In this paper, a multiple feature regularized kernel is proposed for hyperspectral imagery classification. To exploit the label information, a regularized kernel is used to refine the original kernel in the Support Vector Machine classifier. Furthermore, since spatial features have been widely investigated for hyperspectral imagery classification, different types of spatial features including spectral feature, local feature (i.e. local binary pattern), global feature (i.e. Gabor feature), and shape feature (i.e. extended multiattribute profiles) are included to provide distinguish discriminative information. Finally, a majority voting-based ensemble approach, which combines different types of features, is adopted to further increase the classification performance. Combining different discriminative feature information can improve the classification performance since one type of feature may result in poor performance, especially when the number of training samples is limited. Experimental results demonstrated that the proposed approach has superior performance compared with the state-of-the-art classifiers.

DOI:10.1017/ATSIP.2020.8