Identity statement area
Reference TypeConference Proceedings
Last Update2006: administrator
Metadata Last Update2020: administrator
Citation KeyFreryFerrBust:2006:AcStCl
TitleAccuracy of Statistical Classification Strategies in Remote Sensing Imagery
Date8-11 Oct. 2006
Access Date2020, Dec. 03
Number of Files1
Size265 KiB
Context area
Author1 Frery, Alejandro César
2 Ferrero, Susana
3 Bustos, Oscar Humberto
Affiliation1 Universidade Federal de Alagoas
2 Universidad Nacional de Río Cuarto
3 Universidad Nacional de Córdoba
EditorOliveira Neto, Manuel Menezes de
Carceroni, Rodrigo Lima
Conference NameBrazilian Symposium on Computer Graphics and Image Processing, 19 (SIBGRAPI)
Conference LocationManaus
Book TitleProceedings
PublisherIEEE Computer Society
Publisher CityLos Alamitos
History2006-07-18 12:53:07 :: acfrery -> banon ::
2006-08-30 21:52:16 :: banon -> acfrery ::
2008-07-17 14:11:03 :: acfrery -> administrator ::
2009-08-13 20:38:08 :: administrator -> banon ::
2010-08-28 20:02:24 :: banon -> administrator ::
2020-02-19 03:17:40 :: administrator -> :: 2006
Content and structure area
Is the master or a copy?is the master
Document Stagecompleted
Content TypeExternal Contribution
Tertiary TypeFull Paper
Keywordsimage classification, accuracy, contextual classification.
AbstractWe present the assessment of two classification procedures using a Monte Carlo experience and Landsat data. Classification performance is hard to assess with generality due to the huge number of variables involved. In this case we consider the problem of classifying multispectral optical imagery with pointwise Gaussian Maximum Likelihood and contextual ICM (Iterated Conditional Modes), with and without errors in the training stage. Using simulation the ground truth is known and, therefore, precise comparisons are possible. The contextual approach proved being superior than the pointwise one, at the expense of requiring more computational resources, with both real and simulated data. Quantitative and qualitative results are discussed.
source Directory Contentthere are no files
agreement Directory Contentthere are no files
Conditions of access and use area
Target Filefrery-AccuracyClassification.pdf
User Groupacfrery
Allied materials area
Notes area
Empty Fieldsaccessionnumber archivingpolicy archivist area callnumber copyholder copyright creatorhistory descriptionlevel dissemination documentstage doi edition electronicmailaddress group holdercode isbn issn label lineage mark mirrorrepository nextedition nexthigherunit notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url versiontype volume