This title appears in the Scientific Report : 2017 
Automatic Attribute Profiles
Cavallaro, Gabriele (Corresponding author)
Falco, Nicola / Dalla Mura, Mauro / Benediktsson, Jon Atli
Jülich Supercomputing Center; JSC
IEEE transactions on image processing, 26 (2017) 4, S. 1859 - 1872
New York, NY IEEE 2017
10.1109/TIP.2017.2664667
Journal Article
Enabling Intelligent GMES Services for Carbon and Water Balance Modeling of Northern Forest Ecosystems
Data-Intensive Science and Federated Computing
Please use the identifier: http://dx.doi.org/10.1109/TIP.2017.2664667 in citations.

LEADER 05357nam a2200697 a 4500
001 840596
005 20210129231852.0
024 7 |a 10.1109/TIP.2017.2664667  |2 doi 
024 7 |a 1057-7149  |2 ISSN 
024 7 |a 1941-0042  |2 ISSN 
024 7 |a WOS:000398976000006  |2 WOS 
037 |a FZJ-2017-08101 
082 |a 004 
100 1 |a Cavallaro, Gabriele  |0 P:(DE-Juel1)171343  |b 0  |e Corresponding author  |u fzj 
245 |a Automatic Attribute Profiles 
260 |a New York, NY  |c 2017  |b IEEE 
520 |a Morphological 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. 
588 |a Dataset connected to CrossRef 
700 1 |a Falco, Nicola  |0 P:(DE-HGF)0  |b 1 
700 1 |a Dalla Mura, Mauro  |0 0000-0002-9656-9087  |b 2 
700 1 |a Benediktsson, Jon Atli  |0 P:(DE-HGF)0  |b 3 
773 |a 10.1109/TIP.2017.2664667  |g Vol. 26, no. 4, p. 1859 - 1872  |0 PERI:(DE-600)2034319-X  |n 4  |p 1859 - 1872  |t IEEE transactions on image processing  |v 26  |y 2017  |x 1941-0042 
856 4 |u http://juser.fz-juelich.de/record/840596/files/07842555.pdf  |y Restricted 
856 4 |u http://juser.fz-juelich.de/record/840596/files/07842555.gif?subformat=icon  |x icon  |y Restricted 
856 4 |u http://juser.fz-juelich.de/record/840596/files/07842555.jpg?subformat=icon-1440  |x icon-1440  |y Restricted 
856 4 |u http://juser.fz-juelich.de/record/840596/files/07842555.jpg?subformat=icon-180  |x icon-180  |y Restricted 
856 4 |u http://juser.fz-juelich.de/record/840596/files/07842555.jpg?subformat=icon-640  |x icon-640  |y Restricted 
856 4 |u http://juser.fz-juelich.de/record/840596/files/07842555.pdf?subformat=pdfa  |x pdfa  |y Restricted 
909 C O |o oai:juser.fz-juelich.de:840596  |p openaire  |p VDB  |p ec_fundedresources 
910 1 |a Forschungszentrum Jülich  |0 I:(DE-588b)5008462-8  |k FZJ  |b 0  |6 P:(DE-Juel1)171343 
913 1 |a DE-HGF  |b Key Technologies  |1 G:(DE-HGF)POF3-510  |0 G:(DE-HGF)POF3-512  |2 G:(DE-HGF)POF3-500  |v Data-Intensive Science and Federated Computing  |x 0  |4 G:(DE-HGF)POF  |3 G:(DE-HGF)POF3  |l Supercomputing & Big Data 
914 1 |y 2017 
915 |a DBCoverage  |0 StatID:(DE-HGF)0300  |2 StatID  |b Medline 
915 |a DBCoverage  |0 StatID:(DE-HGF)0310  |2 StatID  |b NCBI Molecular Biology Database 
915 |a JCR  |0 StatID:(DE-HGF)0100  |2 StatID  |b IEEE T IMAGE PROCESS : 2015 
915 |a DBCoverage  |0 StatID:(DE-HGF)0200  |2 StatID  |b SCOPUS 
915 |a DBCoverage  |0 StatID:(DE-HGF)0600  |2 StatID  |b Ebsco Academic Search 
915 |a Peer Review  |0 StatID:(DE-HGF)0030  |2 StatID  |b ASC 
915 |a DBCoverage  |0 StatID:(DE-HGF)0199  |2 StatID  |b Thomson Reuters Master Journal List 
915 |a WoS  |0 StatID:(DE-HGF)0110  |2 StatID  |b Science Citation Index 
915 |a DBCoverage  |0 StatID:(DE-HGF)0150  |2 StatID  |b Web of Science Core Collection 
915 |a WoS  |0 StatID:(DE-HGF)0111  |2 StatID  |b Science Citation Index Expanded 
915 |a DBCoverage  |0 StatID:(DE-HGF)1160  |2 StatID  |b Current Contents - Engineering, Computing and Technology 
915 |a IF < 5  |0 StatID:(DE-HGF)9900  |2 StatID 
980 |a journal 
980 |a VDB 
980 |a I:(DE-Juel1)JSC-20090406 
980 |a UNRESTRICTED 
536 |a Enabling Intelligent GMES Services for Carbon and Water Balance Modeling of Northern Forest Ecosystems  |0 G:(EU-Grant)606962  |c 606962  |f FP7-SPACE-2013-1  |x 1 
536 |a Data-Intensive Science and Federated Computing  |0 G:(DE-HGF)POF3-512  |c POF3-512  |f POF III  |x 0 
336 |a ARTICLE  |2 BibTeX 
336 |a Journal Article  |b journal  |m journal  |0 PUB:(DE-HGF)16  |s 1512572817_21217  |2 PUB:(DE-HGF) 
336 |a Output Types/Journal article  |2 DataCite 
336 |a article  |2 DRIVER 
336 |a Nanopartikel unedler Metalle (Mg0, Al0, Gd0, Sm0)  |0 0  |2 EndNote 
336 |a JOURNAL_ARTICLE  |2 ORCID 
920 |k Jülich Supercomputing Center; JSC  |0 I:(DE-Juel1)JSC-20090406  |l Jülich Supercomputing Center  |x 0 
990 |a Cavallaro, Gabriele  |0 P:(DE-Juel1)171343  |b 0  |e Corresponding author  |u fzj 
991 |a Benediktsson, Jon Atli  |0 P:(DE-HGF)0  |b 3 
991 |a Dalla Mura, Mauro  |0 0000-0002-9656-9087  |b 2 
991 |a Falco, Nicola  |0 P:(DE-HGF)0  |b 1