Skip to main navigation Skip to search Skip to main content

Locality-preserving nonnegative matrix factorization for hyperspectral image classification

  • Wei Li*
  • , Saurabh Prasad
  • , James E. Fowler
  • , Minshan Cui
  • *Corresponding author for this work
  • Mississippi State University
  • University of Houston

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

Abstract

Feature extraction based on nonnegative matrix factorization is considered for hyperspectral image classification. One shortcoming of most remote-sensing data is low spatial resolution, which causes a pixel to be mixed with several pure spectral signatures, or endmembers. To counter this effect, locality-preserving nonnegative matrix factorization is employed in order to extract an endmembers-based feature representation as well as to preserve the intrinsic geometric structure of hyperspectral data. Subsequently, a Gaussian mixture model classifier is employed in the induced-feature subspace. Experimental results demonstrate that the proposed classification system significantly outperforms traditional approaches even in instances of limited training data and severe pixel mixing.

Original languageEnglish
Title of host publicationIGARSS 2012 - 2012 IEEE International Geoscience and Remote Sensing Symposium
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1405-1408
Number of pages4
ISBN (Electronic)9781467311595
DOIs
Publication statusPublished - 2012
Externally publishedYes
Event32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012 - Munich, Germany
Duration: 22 Jul 201227 Jul 2012

Publication series

NameInternational Geoscience and Remote Sensing Symposium (IGARSS)
ISSN (Print)2153-6996
ISSN (Electronic)2153-7003

Conference

Conference32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012
Country/TerritoryGermany
CityMunich
Period22/07/1227/07/12

Keywords

  • feature extraction
  • Linear mixing model
  • nonnegative matrix factorization
  • pattern classification

Fingerprint

Dive into the research topics of 'Locality-preserving nonnegative matrix factorization for hyperspectral image classification'. Together they form a unique fingerprint.

Cite this