Next Article in Journal
On the Potential of Robust Satellite Techniques Approach for SPM Monitoring in Coastal Waters: Implementation and Application over the Basilicata Ionian Coastal Waters Using MODIS‐Aqua
Previous Article in Journal
Impacts of Temporal-Spatial Variant Background Ionosphere on Repeat-Track GEO D-InSAR System
Open AccessArticle

A Spectral-Texture Kernel-Based Classification Method for Hyperspectral Images

by *,†, and
Institute of Geophysics and Geomatics, China University of Geosciences, Wuhan 430074, China
*
Author to whom correspondence should be addressed.
These authors contributed equally to this work.
Academic Editors: Lenio Soares Galvao and Prasad S. Thenkabail
Remote Sens. 2016, 8(11), 919; https://doi.org/10.3390/rs8110919
Received: 1 September 2016 / Revised: 27 October 2016 / Accepted: 28 October 2016 / Published: 5 November 2016
Classification of hyperspectral images always suffers from high dimensionality and very limited labeled samples. Recently, the spectral-spatial classification has attracted considerable attention and can achieve higher classification accuracy and smoother classification maps. In this paper, a novel spectral-spatial classification method for hyperspectral images by using kernel methods is investigated. For a given hyperspectral image, the principle component analysis (PCA) transform is first performed. Then, the first principle component of the input image is segmented into non-overlapping homogeneous regions by using the entropy rate superpixel (ERS) algorithm. Next, the local spectral histogram model is applied to each homogeneous region to obtain the corresponding texture features. Because this step is performed within each homogenous region, instead of within a fixed-size image window, the obtained local texture features in the image are more accurate, which can effectively benefit the improvement of classification accuracy. In the following step, a contextual spectral-texture kernel is constructed by combining spectral information in the image and the extracted texture information using the linearity property of the kernel methods. Finally, the classification map is achieved by the support vector machines (SVM) classifier using the proposed spectral-texture kernel. Experiments on two benchmark airborne hyperspectral datasets demonstrate that our method can effectively improve classification accuracies, even though only a very limited training sample is available. Specifically, our method can achieve from 8.26% to 15.1% higher in terms of overall accuracy than the traditional SVM classifier. The performance of our method was further compared to several state-of-the-art classification methods of hyperspectral images using objective quantitative measures and a visual qualitative evaluation. View Full-Text
Keywords: hyperspectral images; classification; spectral-spatial; texture; entropy rate superpixel; local spectral histogram hyperspectral images; classification; spectral-spatial; texture; entropy rate superpixel; local spectral histogram
Show Figures

Graphical abstract

MDPI and ACS Style

Wang, Y.; Zhang, Y.; Song, H. A Spectral-Texture Kernel-Based Classification Method for Hyperspectral Images. Remote Sens. 2016, 8, 919. https://doi.org/10.3390/rs8110919

AMA Style

Wang Y, Zhang Y, Song H. A Spectral-Texture Kernel-Based Classification Method for Hyperspectral Images. Remote Sensing. 2016; 8(11):919. https://doi.org/10.3390/rs8110919

Chicago/Turabian Style

Wang, Yi; Zhang, Yan; Song, Haiwei. 2016. "A Spectral-Texture Kernel-Based Classification Method for Hyperspectral Images" Remote Sens. 8, no. 11: 919. https://doi.org/10.3390/rs8110919

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop