000840596 001__ 840596
000840596 005__ 20210129231852.0
000840596 0247_ $$2doi$$a10.1109/TIP.2017.2664667
000840596 0247_ $$2ISSN$$a1057-7149
000840596 0247_ $$2ISSN$$a1941-0042
000840596 0247_ $$2WOS$$aWOS:000398976000006
000840596 037__ $$aFZJ-2017-08101
000840596 082__ $$a004
000840596 1001_ $$0P:(DE-Juel1)171343$$aCavallaro, Gabriele$$b0$$eCorresponding author$$ufzj
000840596 245__ $$aAutomatic Attribute Profiles
000840596 260__ $$aNew York, NY$$bIEEE$$c2017
000840596 3367_ $$2DRIVER$$aarticle
000840596 3367_ $$2DataCite$$aOutput Types/Journal article
000840596 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1512572817_21217
000840596 3367_ $$2BibTeX$$aARTICLE
000840596 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000840596 3367_ $$00$$2EndNote$$aJournal Article
000840596 520__ $$aMorphological attribute profiles are multilevel decompositions of images obtained with a sequence of transformations performed by connected operators. They have been extensively employed in performing multiscale and region-based analysis in a large number of applications. One main, still unresolved, issue is the selection of filter parameters able to provide representative and non-redundant threshold decomposition of the image. This paper presents a framework for the automatic selection of filter thresholds based on Granulometric Characteristic Functions (GCFs). GCFs describe the way that non-linear morphological filters simplify a scene according to a given measure. Since attribute filters rely on a hierarchical representation of an image (e.g., the Tree of Shapes) for their implementation, GCFs can be efficiently computed by taking advantage of the tree representation. Eventually, the study of the GCFs allows the identification of a meaningful set of thresholds. Therefore, a trial and error approach is not necessary for the threshold selection, automating the process and in turn decreasing the computational time. It is shown that the redundant information is reduced within the resulting profiles (a problem of high occurrence, as regards manual selection). The proposed approach is tested on two real remote sensing data sets, and the classification results are compared with strategies present in the literature.
000840596 536__ $$0G:(DE-HGF)POF3-512$$a512 - Data-Intensive Science and Federated Computing (POF3-512)$$cPOF3-512$$fPOF III$$x0
000840596 536__ $$0G:(EU-Grant)606962$$aNORTH STATE - Enabling Intelligent GMES Services for Carbon and Water Balance Modeling of Northern Forest Ecosystems (606962)$$c606962$$fFP7-SPACE-2013-1$$x1
000840596 588__ $$aDataset connected to CrossRef
000840596 7001_ $$0P:(DE-HGF)0$$aFalco, Nicola$$b1
000840596 7001_ $$00000-0002-9656-9087$$aDalla Mura, Mauro$$b2
000840596 7001_ $$0P:(DE-HGF)0$$aBenediktsson, Jon Atli$$b3
000840596 773__ $$0PERI:(DE-600)2034319-X$$a10.1109/TIP.2017.2664667$$gVol. 26, no. 4, p. 1859 - 1872$$n4$$p1859 - 1872$$tIEEE transactions on image processing$$v26$$x1941-0042$$y2017
000840596 8564_ $$uhttps://juser.fz-juelich.de/record/840596/files/07842555.pdf$$yRestricted
000840596 8564_ $$uhttps://juser.fz-juelich.de/record/840596/files/07842555.gif?subformat=icon$$xicon$$yRestricted
000840596 8564_ $$uhttps://juser.fz-juelich.de/record/840596/files/07842555.jpg?subformat=icon-1440$$xicon-1440$$yRestricted
000840596 8564_ $$uhttps://juser.fz-juelich.de/record/840596/files/07842555.jpg?subformat=icon-180$$xicon-180$$yRestricted
000840596 8564_ $$uhttps://juser.fz-juelich.de/record/840596/files/07842555.jpg?subformat=icon-640$$xicon-640$$yRestricted
000840596 8564_ $$uhttps://juser.fz-juelich.de/record/840596/files/07842555.pdf?subformat=pdfa$$xpdfa$$yRestricted
000840596 909CO $$ooai:juser.fz-juelich.de:840596$$pec_fundedresources$$pVDB$$popenaire
000840596 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)171343$$aForschungszentrum Jülich$$b0$$kFZJ
000840596 9131_ $$0G:(DE-HGF)POF3-512$$1G:(DE-HGF)POF3-510$$2G:(DE-HGF)POF3-500$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bKey Technologies$$lSupercomputing & Big Data$$vData-Intensive Science and Federated Computing$$x0
000840596 9141_ $$y2017
000840596 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline
000840596 915__ $$0StatID:(DE-HGF)0310$$2StatID$$aDBCoverage$$bNCBI Molecular Biology Database
000840596 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bIEEE T IMAGE PROCESS : 2015
000840596 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS
000840596 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search
000840596 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC
000840596 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bThomson Reuters Master Journal List
000840596 915__ $$0StatID:(DE-HGF)0110$$2StatID$$aWoS$$bScience Citation Index
000840596 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection
000840596 915__ $$0StatID:(DE-HGF)0111$$2StatID$$aWoS$$bScience Citation Index Expanded
000840596 915__ $$0StatID:(DE-HGF)1160$$2StatID$$aDBCoverage$$bCurrent Contents - Engineering, Computing and Technology
000840596 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5
000840596 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
000840596 980__ $$ajournal
000840596 980__ $$aVDB
000840596 980__ $$aI:(DE-Juel1)JSC-20090406
000840596 980__ $$aUNRESTRICTED