Skip navigation
Skip navigation
A change is coming. Click to see a sneak peek of the new Open Research Repository.

Using Suitable Neighbors to Augment the Training Set in Hyperspectral Maximum Likelihood Classification

Request a Copy

link to publisher version

  • Altmetric Citations

Richards, John; Jia, Xiuping

Description

A method is presented for supplementing the training set in maximum likelihood classification of hyperspectral data to mitigate the Hughes phenomenon. Based on the idea that the near neighbors of training pixels are likely to come from the same class, measures are proposed to assess neighbors as potential candidates so that those selected give improved class statistics and classification accuracy.

dc.contributor.authorRichards, John
dc.contributor.authorJia, Xiuping
dc.date.accessioned2015-12-08T22:21:45Z
dc.identifier.issn1545-598X
dc.identifier.urihttp://hdl.handle.net/1885/32257
dc.description.abstractA method is presented for supplementing the training set in maximum likelihood classification of hyperspectral data to mitigate the Hughes phenomenon. Based on the idea that the near neighbors of training pixels are likely to come from the same class, measures are proposed to assess neighbors as potential candidates so that those selected give improved class statistics and classification accuracy.
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE Inc)
dc.sourceIEEE Geoscience and Remote Sensing Letters
dc.subjectKeywords: Atmospherics; Image sensors; Maximum likelihood; Quadrature phase shift keying; Class statistics; Classification; Classification accuracies; Generalization; Hughes phenomenons; Hyperspectral; Hyperspectral datums; Maximum likelihood classifications; Train Classification; Generalization; Hyperspectral; Training
dc.titleUsing Suitable Neighbors to Augment the Training Set in Hyperspectral Maximum Likelihood Classification
dc.typeJournal article
local.description.notesImported from ARIES
local.identifier.citationvolume5
dc.date.issued2008
local.identifier.absfor080109 - Pattern Recognition and Data Mining
local.identifier.ariespublicationu4334215xPUB90
local.type.statusPublished Version
local.contributor.affiliationRichards, John, College of Engineering and Computer Science, ANU
local.contributor.affiliationJia, Xiuping, University of New South Wales
local.description.embargo2037-12-31
local.bibliographicCitation.issue4
local.bibliographicCitation.startpage774
local.bibliographicCitation.lastpage777
local.identifier.doi10.1109/LGRS.2008.2005512
dc.date.updated2016-02-24T11:04:07Z
local.identifier.scopusID2-s2.0-55649083745
local.identifier.thomsonID000260956600046
CollectionsANU Research Publications

Download

File Description SizeFormat Image
01_Richards_Using_Suitable_Neighbors_to_2008.pdf261.36 kBAdobe PDF    Request a copy
Show simple item record


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  17 November 2022/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator