Classification of hyperspectral image using multiscale spatial texture features

Paheding Sidike, Chen Chen, Vijayan Asari, Yan Xu, Wei Li*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

19 Citations (Scopus)

Abstract

Spatial information has shown significant contribution for hyperspectral image classification. Local Binary Pattern (LBP) can be used for extracting spatial texture features, however it is incapable of capturing textural and structural features of images at various resolution. Hence, we present a multiscale scheme on Complete LBP (CLBP) as well as on LBP to obtain better spatial features from hyperspectral imagery (HSI). Experiments conducted on two standard HSI datasets proved that the proposed multiscale scheme can improve the classification accuracy of both LBP and CLBP, and Multiscale CLBP provides better accuracy compared to the state-of-the-art spatial feature extraction methods for HSI classification.

Original languageEnglish
Title of host publication2016 8th Workshop on Hyperspectral Image and Signal Processing
Subtitle of host publicationEvolution in Remote Sensing, WHISPERS 2016
PublisherIEEE Computer Society
ISBN (Electronic)9781509006083
DOIs
Publication statusPublished - 28 Jun 2016
Externally publishedYes
Event8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2016 - Los Angeles, United States
Duration: 21 Aug 201624 Aug 2016

Publication series

NameWorkshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing
Volume0
ISSN (Print)2158-6276

Conference

Conference8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2016
Country/TerritoryUnited States
CityLos Angeles
Period21/08/1624/08/16

Keywords

  • Completed local binary pattern (CLBP)
  • Extreme learning machine (ELM)
  • Hyperspectral imagery (HSI)
  • Image classification
  • Local binary pattern (LBP)

Fingerprint

Dive into the research topics of 'Classification of hyperspectral image using multiscale spatial texture features'. Together they form a unique fingerprint.

Cite this