Close
Metadata

1. Identity statement
Reference TypeJournal Article
Sitemtc-m21b.sid.inpe.br
Holder Codeisadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S
Identifier8JMKD3MGP3W34P/3JNG795
Repositorysid.inpe.br/mtc-m21b/2015/06.24.11.47   (restricted access)
Last Update2015:06.24.11.47.38 (UTC) administrator
Metadata Repositorysid.inpe.br/mtc-m21b/2015/06.24.11.47.38
Metadata Last Update2018:06.04.02.55.28 (UTC) administrator
ISSN0219-4678
Citation KeyCarvalhoManSobComWan:2015:ImGrIm
TitleImproving graph-based image segmentation using non-linear color similarity metrics
Year2015
MonthJune
Access Date2024, May 19
Type of Workjournal article
Secondary TypePRE PI
Number of Files1
Size2759 KiB
2. Context
Author1 Carvalho, L. E.
2 Mantelli Neto, Sylvio Luiz
3 Sobieranski, A. C.
4 Comunello, Eros
5 von Wangenheim, A.
Resume Identifier1
2 8JMKD3MGP5W/3C9JJ9K
Group1
2 CST-CST-INPE-MCTI-GOV-BR
Affiliation1 Universidade Federal de Santa Catarina (UFSC)
2 Instituto Nacional de Pesquisas Espaciais (INPE)
3 Universidade Federal de Santa Catarina (UFSC)
4 Universidade Federal de Santa Catarina (UFSC)
5 Universidade Federal de Santa Catarina (UFSC)
Author e-Mail Address1 lcarvalho@incod.ufsc.br
2 sylvio.mantelli@inpe.br
3 asobieranski@incod.ufsc.br
4 eros@incod.ufsc.br
5 awangenh@inf.ufsc.br
JournalInternational Journal of Image and Graphics
Volume16
Number21
Secondary MarkB2_CIÊNCIA_DA_COMPUTAÇÃO
History (UTC)2015-06-24 11:47:38 :: simone -> administrator ::
2018-06-04 02:55:28 :: administrator -> simone :: 2015
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Content TypeExternal Contribution
Version Typefinaldraft
KeywordsFelzenszwalb and Huttenlocher method
Polynomial Mahalanobis Distance
Non-Linear Color Similarity Metrics
AbstractWe present a new segmentation method called Weighted Felzenszwalb and Hutten-locher method (WFH), an improved version of the well-known graph-based segmentation method, Felzenszwalb and Huttenlocher method (FH). Our method uses a non-linear discrimination function based on Polynomial Mahalanobis Distance (PMD) as the color similarity metric. Two empirical validation experiments were performed using as a golden standard ground truths from a publicly available source, the Berkeley dataset, and an objective segmentation quality measure, the Rand dissimilarity index. In the first experiment the results were compared against the original FH method. In the second, WFH was compared against several well-known segmentation methods. In both cases WFH presented significant better similarity results when compared with the golden standard and segmentation results presented a reduction of over-segmented regions.
AreaCST
Arrangementurlib.net > BDMCI > Fonds > Produção anterior à 2021 > COCST > Improving graph-based image...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Content
agreement.html 24/06/2015 08:47 1.0 KiB 
4. Conditions of access and use
Languageen
Target Filecarvalho_improving.pdf
User Groupsimone
Reader Groupadministrator
simone
Visibilityshown
Read Permissiondeny from all and allow from 150.163
Update Permissionnot transferred
5. Allied materials
Mirror Repositoryurlib.net/www/2011/03.29.20.55
Next Higher Units8JMKD3MGPCW/3F3T29H
Citing Item Listsid.inpe.br/bibdigital/2013/10.19.20.40 3
sid.inpe.br/mtc-m21/2012/07.13.15.00.44 2
DisseminationWEBSCI; PORTALCAPES.
Host Collectionsid.inpe.br/mtc-m21b/2013/09.26.14.25.20
6. Notes
Empty Fieldsalternatejournal archivingpolicy archivist callnumber copyholder copyright creatorhistory descriptionlevel doi e-mailaddress format isbn label lineage mark nextedition notes orcid pages parameterlist parentrepositories previousedition previouslowerunit progress project rightsholder schedulinginformation secondarydate secondarykey session shorttitle sponsor subject tertiarymark tertiarytype url
7. Description control
e-Mail (login)simone
update 


Close