Spectral-spatial classification of hyperspectral data using spectral-domain local binary patterns

Cai-ling Wang, Jinchang Ren, Hong-wei Wang, Yinyong Zhang, Jia Wen

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

It is of great interest in spectral-spatial features classification for hyperspectral images (HSI) with high spatial resolution. This paper presents a novel Spectral-spatial classification method for improving hyperspectral image classification accuracy. Specifically, a new texture feature extraction algorithm exploits spatial texture feature from spectrum is proposed. It employs local binary patterns (LBPs) in order to extract the image texture feature with respect to spectrum information diversity (SID) to measure the differences of spectrum information. The classifier adopted in this work is support vector machine (SVM) because of its outstanding classification performances. In this paper, two real hyperspectral image datasets are used for testing the performance of the proposed method. Our experimental results from real hyperspectral images indicate that the proposed framework can enhance the classification accuracy compare to traditional alternatives.
LanguageEnglish
Pages29889-29903
Number of pages15
JournalMultimedia Tools and Applications
Volume77
Issue number22
Early online date11 Apr 2018
DOIs
Publication statusPublished - 30 Nov 2018

Fingerprint

Textures
Image texture
Image classification
Support vector machines
Feature extraction
Classifiers
Testing

Keywords

  • hyperspectral image classification
  • spectral-spatial analysis
  • local binary patterns
  • spectrum information diversity
  • support vector machine

Cite this

@article{ee76b6d0d0be4f98900ceeccde57a409,
title = "Spectral-spatial classification of hyperspectral data using spectral-domain local binary patterns",
abstract = "It is of great interest in spectral-spatial features classification for hyperspectral images (HSI) with high spatial resolution. This paper presents a novel Spectral-spatial classification method for improving hyperspectral image classification accuracy. Specifically, a new texture feature extraction algorithm exploits spatial texture feature from spectrum is proposed. It employs local binary patterns (LBPs) in order to extract the image texture feature with respect to spectrum information diversity (SID) to measure the differences of spectrum information. The classifier adopted in this work is support vector machine (SVM) because of its outstanding classification performances. In this paper, two real hyperspectral image datasets are used for testing the performance of the proposed method. Our experimental results from real hyperspectral images indicate that the proposed framework can enhance the classification accuracy compare to traditional alternatives.",
keywords = "hyperspectral image classification , spectral-spatial analysis, local binary patterns , spectrum information diversity, support vector machine",
author = "Cai-ling Wang and Jinchang Ren and Hong-wei Wang and Yinyong Zhang and Jia Wen",
year = "2018",
month = "11",
day = "30",
doi = "10.1007/s11042-018-5928-2",
language = "English",
volume = "77",
pages = "29889--29903",
journal = "Multimedia Tools and Applications",
issn = "1380-7501",
number = "22",

}

Spectral-spatial classification of hyperspectral data using spectral-domain local binary patterns. / Wang, Cai-ling; Ren, Jinchang; Wang, Hong-wei; Zhang, Yinyong; Wen, Jia.

In: Multimedia Tools and Applications, Vol. 77, No. 22, 30.11.2018, p. 29889-29903.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Spectral-spatial classification of hyperspectral data using spectral-domain local binary patterns

AU - Wang, Cai-ling

AU - Ren, Jinchang

AU - Wang, Hong-wei

AU - Zhang, Yinyong

AU - Wen, Jia

PY - 2018/11/30

Y1 - 2018/11/30

N2 - It is of great interest in spectral-spatial features classification for hyperspectral images (HSI) with high spatial resolution. This paper presents a novel Spectral-spatial classification method for improving hyperspectral image classification accuracy. Specifically, a new texture feature extraction algorithm exploits spatial texture feature from spectrum is proposed. It employs local binary patterns (LBPs) in order to extract the image texture feature with respect to spectrum information diversity (SID) to measure the differences of spectrum information. The classifier adopted in this work is support vector machine (SVM) because of its outstanding classification performances. In this paper, two real hyperspectral image datasets are used for testing the performance of the proposed method. Our experimental results from real hyperspectral images indicate that the proposed framework can enhance the classification accuracy compare to traditional alternatives.

AB - It is of great interest in spectral-spatial features classification for hyperspectral images (HSI) with high spatial resolution. This paper presents a novel Spectral-spatial classification method for improving hyperspectral image classification accuracy. Specifically, a new texture feature extraction algorithm exploits spatial texture feature from spectrum is proposed. It employs local binary patterns (LBPs) in order to extract the image texture feature with respect to spectrum information diversity (SID) to measure the differences of spectrum information. The classifier adopted in this work is support vector machine (SVM) because of its outstanding classification performances. In this paper, two real hyperspectral image datasets are used for testing the performance of the proposed method. Our experimental results from real hyperspectral images indicate that the proposed framework can enhance the classification accuracy compare to traditional alternatives.

KW - hyperspectral image classification

KW - spectral-spatial analysis

KW - local binary patterns

KW - spectrum information diversity

KW - support vector machine

U2 - 10.1007/s11042-018-5928-2

DO - 10.1007/s11042-018-5928-2

M3 - Article

VL - 77

SP - 29889

EP - 29903

JO - Multimedia Tools and Applications

T2 - Multimedia Tools and Applications

JF - Multimedia Tools and Applications

SN - 1380-7501

IS - 22

ER -