The effect of training data on hyperspectral classification algorithms

In this study, the performance of different hyperspectral classification algorithms with the same training set is investigated. In addition, the effect of the dimension and sampling strategy for the training set selection is demonstrated. Support Vector Machines (SVM), K- Nearest Neighbor (K-NN) and...

Full description

Saved in:
Bibliographic Details
Published in2013 21st Signal Processing and Communications Applications Conference (SIU) pp. 1 - 4
Main Authors Ozdemir, Okan Bilge, Cetin, Y. Y.
Format Conference Proceeding
LanguageEnglish
Turkish
Published IEEE 01.04.2013
Subjects
Classification algorithms
Hyperspectral Classification
Hyperspectral imaging
K-Nearest Neighbor
Kernel
Maximum Likelihood
Support vector machines
Training
Online AccessGet full text

Cover

Abstract In this study, the performance of different hyperspectral classification algorithms with the same training set is investigated. In addition, the effect of the dimension and sampling strategy for the training set selection is demonstrated. Support Vector Machines (SVM), K- Nearest Neighbor (K-NN) and Maximum Likelihood (ML) methods are used. The contribution of using spatial information with spectral information is observed. Meanshift segmentation and window weighting methods are used for spatial information. High resolution Pavia University hyperspectral data and Indian Pines data are used in this study.
AbstractList In this study, the performance of different hyperspectral classification algorithms with the same training set is investigated. In addition, the effect of the dimension and sampling strategy for the training set selection is demonstrated. Support Vector Machines (SVM), K- Nearest Neighbor (K-NN) and Maximum Likelihood (ML) methods are used. The contribution of using spatial information with spectral information is observed. Meanshift segmentation and window weighting methods are used for spatial information. High resolution Pavia University hyperspectral data and Indian Pines data are used in this study.
Author Ozdemir, Okan Bilge
Cetin, Y. Y.
Author_xml – sequence: 1
  givenname: Okan Bilge
  surname: Ozdemir
  fullname: Ozdemir, Okan Bilge
  email: oozdemir@metu.edu.tr
  organization: Enformatik Enstitusu, Orta Dogu Teknik Univ., Ankara, Turkey
– sequence: 2
  givenname: Y. Y.
  surname: Cetin
  fullname: Cetin, Y. Y.
  email: yyardim@metu.edu.tr
  organization: Enformatik Enstitusu, Orta Dogu Teknik Univ., Ankara, Turkey
BookMark eNpVj8FKAzEURSMqqHX2gpv8QOtLMkkmSylWCwUX1nV5k3mvjUxnhsls-vcW7MbV5XI4F-6DuOn6joR4UrBQCsLL1_p7oUGZhbNGGW2uRBF8pUrnjbXOuOt_XYc7UeT8AwBn24XK3YvV9kCSmClOsmc5jZi61O1lgxPKvpOH00BjHs54xFbGFnNOnCJO6Qyx3fdjmg7H_ChuGdtMxSVnYrt62y4_5pvP9_XydTNPCuw0Z0SrfMXaBCpdLFnV7JpoLVgkdkHXoL1qNIKPDkFzaLgpS649RQIwM_H8N5uIaDeM6YjjaXc5b34BWTlPvA
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/SIU.2013.6531323
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library Online
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9781467355636
1467355631
1467355615
9781467355612
EndPage 4
ExternalDocumentID 6531323
Genre orig-research
GroupedDBID 6IE
6IF
6IK
6IL
6IN
AAJGR
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
IEGSK
IERZE
OCL
RIE
RIL
ID FETCH-LOGICAL-i105t-faa5178f239e46c4f1bf6dc5505aef692b0271d2a07c6a02f9dfd44fb7ece003
IEDL.DBID RIE
ISBN 9781467355629
1467355623
IngestDate Wed Jun 26 19:24:39 EDT 2024
IsPeerReviewed false
IsScholarly false
Language English
Turkish
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i105t-faa5178f239e46c4f1bf6dc5505aef692b0271d2a07c6a02f9dfd44fb7ece003
PageCount 4
ParticipantIDs ieee_primary_6531323
PublicationCentury 2000
PublicationDate 2013-April
PublicationDateYYYYMMDD 2013-04-01
PublicationDate_xml – month: 04
  year: 2013
  text: 2013-April
PublicationDecade 2010
PublicationTitle 2013 21st Signal Processing and Communications Applications Conference (SIU)
PublicationTitleAbbrev SIU
PublicationYear 2013
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0001106986
Score 1.5401888
Snippet In this study, the performance of different hyperspectral classification algorithms with the same training set is investigated. In addition, the effect of the...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Classification algorithms
Hyperspectral Classification
Hyperspectral imaging
K-Nearest Neighbor
Kernel
Maximum Likelihood
Support vector machines
Training
Title The effect of training data on hyperspectral classification algorithms
URI https://ieeexplore.ieee.org/document/6531323
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV07T8MwELbaTkyAWsRbHhhJ2sSOHzOiKkhFSLRSt8pxbFpREhTShV_P2UlagRiQMuQ8RH5Fd5_9fXcI3SglSEozGwihZUCV4oGkBMyMW2HhYV5fMX1ikzl9XCSLDrrdaWGMMZ58ZkL36u_ys0Jv3VHZkCUu0SDpoi6XstZq7c9TANtIwbx2i3HwouDX25ROjS3ba8qRHL48zB2vi4TNN38UV_G-ZXyIpm2vakrJW7it0lB__UrY-N9uH6HBXsWHn3f-6Rh1TN5HY9gXuCZx4MLitkIEdkxRXOR4Bbi0ll-WaoO1i60dmcivH1ab16JcV6v3zwGaje9nd5OgqaUQrCGCqgKrVBJxYWMiDWWa2ii1LNMOnyhjmYxTwKdRFqsR10yNYiszm1FqU260gT__BPXyIjenCHOXpBDiBKJtSi2gFRIlYMMgNSWCRmeo76Zg-VFny1g2oz__u_kCHcS-wITjwlyiXlVuzRW4-Sq99uv7DdVZo98
link.rule.ids 310,311,783,787,792,793,799,27937,55086
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV09T8MwELVKGWAC1CK-8cBI0iZ2HHtGVAXaColW6lY5jk0rSoJKuvDrOTtJKxADUoach8hf0d2z37tD6EZKThKaGo9zJTwqZewJSsBMY8MNPMzpK4Yj1p_Qx2k0baDbjRZGa-3IZ9q3r-4uP83V2h6VdVhkEw2SHbQLcTVnpVpre6IC6EZw5tRbLAY_Cp69TupU2aK-qOyKzsvDxDK7iF999Ud5FeddegdoWPerJJW8-esi8dXXr5SN_-34IWpvdXz4eeOhjlBDZy3Ug52BSxoHzg2ua0RgyxXFeYbngExLAeZKLrGy0bWlE7kVxHL5mq8Wxfz9s43GvfvxXd-rqil4C4ihCs9IGQUxNyERmjJFTZAYliqLUKQ2TIQJINQgDWU3Vkx2QyNSk1JqklgrDf_-MWpmeaZPEI5tmkKIFIgyCTWAV0gQgQ2DVJRwGpyilp2C2UeZL2NWjf7s7-ZrtNcfDwezwcPo6Rzth67chGXGXKBmsVrrS3D6RXLl1vobnMGnKg
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2013+21st+Signal+Processing+and+Communications+Applications+Conference+%28SIU%29&rft.atitle=The+effect+of+training+data+on+hyperspectral+classification+algorithms&rft.au=Ozdemir%2C+Okan+Bilge&rft.au=Cetin%2C+Y.+Y.&rft.date=2013-04-01&rft.pub=IEEE&rft.isbn=9781467355629&rft.spage=1&rft.epage=4&rft_id=info:doi/10.1109%2FSIU.2013.6531323&rft.externalDocID=6531323
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9781467355629/lc.gif&client=summon&freeimage=true
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9781467355629/mc.gif&client=summon&freeimage=true
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9781467355629/sc.gif&client=summon&freeimage=true