APSIPA Transactions on Signal and Information Processing > Vol 8 > Issue 1

Spectral-spatial feature extraction and supervised classification by MF-KELM classifier on hyperspectral imagery

Wenting Shang, School of Computer Science and Engineering, Nanjing University of Science and Technology, China, Zebin Wu, School of Computer Science and Engineering, Nanjing University of Science and Technology, China, zebin.wu@gmail.com , Yang Xu, School of Computer Science and Engineering, Nanjing University of Science and Technology, China, Yan Zhang, Lianyungang E-Port Information Development Co. Ltd, China, Zhihui Wei, School of Computer Science and Engineering, Nanjing University of Science and Technology, China
 
Suggested Citation
Wenting Shang, Zebin Wu, Yang Xu, Yan Zhang and Zhihui Wei (2019), "Spectral-spatial feature extraction and supervised classification by MF-KELM classifier on hyperspectral imagery", APSIPA Transactions on Signal and Information Processing: Vol. 8: No. 1, e22. http://dx.doi.org/10.1017/ATSIP.2019.15

Publication Date: 20 Sep 2019
© 2019 Wenting Shang, Zebin Wu, Yang Xu, Yan Zhang and Zhihui Wei
 
Subjects
 
Keywords
Kernel extreme learning machine (KELM), Mean filtering (MF) kernel, Spatial bilateral filtering, Spectral band-subsets, Hyperspectral image (HSI), Supervised classification
 

Share

Journal details

Open Access

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

Downloaded: 923 times

In this article:
I. INTRODUCTION 
II. HYPERSPECTRAL IMAGE CLASSIFICATION BASED ON MEAN FILTERING KERNEL EXTREME LEARNING MACHINE 
III. EXPERIMENTS AND ANALYSIS 
IV. CONCLUSION 

Abstract

The kernel extreme learning machine (KELM) is more robust and has a faster learning speed when compared with the traditional neural networks, and thus it is increasingly gaining attention in hyperspectral image (HSI) classification. Although the Gaussian radial basis function kernel widely used in KELM has achieved promising classification performance in supervised HSI classification, it does not consider the underlying data structure of HSIs. In this paper, we propose a novel spectral-spatial KELM method (termed as MF-KELM) by incorporating the mean filtering kernel into the KELM model, which can properly compute the mean value of the spatial neighboring pixels in the kernel space. Considering that in the situation of limited training samples the classification result is very noisy, the spatial bilateral filtering information on spectral band-subsets is introduced to improve the accuracy. Experiment results show that our method outperforms other kernel functions based on KELM in terms of classification accuracy and visual comparison.

DOI:10.1017/ATSIP.2019.15