Hyperspectral images classification based on multiple kernel learning using SWT and KMNF with few training samples

ABSTRACT

In this paper, a new techniquebased on Multiple kernel learning (MKL) with just a few training samples is proposed for HSI classification utilising stationary wavelet transform (SWT) and kernel minimal noise fraction (KMNF). 2D-SWT is applied to each spectral band to discriminate spatial information, and feature sets are created by concatenating wavelet bands. The base kernels associated with each feature set are constructed, and the optimum kernel for maximum separability is learned. The experimental results indicate that the suggested approach provides high accuracy with a low number of training samples and outperforms state-of-the-art MKL-based classifiers with no increase in computing complexity.

KEYWORDS:

• Classification
• hyperspectral images (HSIs)
• multiple kernel learning (MKL)
• stationary wavelet transform (SWT)
• kernel minimum noise fraction (KMNF)

Data availability statement

The dataset that support the findings of this study are openly available to download for Pavia University dataset in Group of Inteligencia Computational (GIC) repository from [http://www.ehu.eus/ccwintco/index.php?title=Hyperspectral_Remote_Sensing_Scenes] and for Indian Pines dataset from [http://lesun.weebly.com/hyperspectral-data-set.html].

Supplementary material

Supplemental data for this article can be accessed online at https://doi.org/10.1080/14498596.2022.2097962.

Disclosure statement

No potential conflict of interest was reported by the authors.

Notes

1. http://www.ehu.eus/ccwintco/index.php?title=Hyperspectral_Remote_Sensing_Scenes.

2. http://lesun.weebly.com/hyperspectral-data-set.html.