Close
Metadata

Identity statement area
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Repositorysid.inpe.br/sibgrapi@80/2007/07.23.17.55
Last Update2007:07.23.17.55.04 administrator
Metadatasid.inpe.br/sibgrapi@80/2007/07.23.17.55.05
Metadata Last Update2020:02.19.03.06.19 administrator
Citation KeyAudigierLotu:2007:SeSeRo
TitleSeed-relative segmentation robustness of watershed and fuzzy connectedness approaches
FormatPrinted, On-line.
Year2007
DateOct. 7-10, 2007
Access Date2021, Jan. 19
Number of Files1
Size176 KiB
Context area
Author1 Audigier, Romaric
2 Lotufo, Roberto de Alencar
Affiliation1 Faculdade de Engenharia Elétrica e de Computação, UNICAMP
2 Faculdade de Engenharia Elétrica e de Computação, UNICAMP
EditorFalcão, Alexandre Xavier
Lopes, Hélio Côrtes Vieira
Conference NameBrazilian Symposium on Computer Graphics and Image Processing, 20 (SIBGRAPI)
Conference LocationBelo Horizonte
Book TitleProceedings
PublisherIEEE Computer Society
Publisher CityLos Alamitos
Tertiary TypeFull Paper
History2007-07-23 17:55:05 :: audigier@dca.fee.unicamp.br -> administrator ::
2007-08-02 21:17:31 :: administrator -> audigier@dca.fee.unicamp.br ::
2008-07-17 14:09:43 :: audigier@dca.fee.unicamp.br -> administrator ::
2009-08-13 20:38:25 :: administrator -> banon ::
2010-08-28 20:02:27 :: banon -> administrator ::
2020-02-19 03:06:19 :: administrator -> :: 2007
Content and structure area
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Content TypeExternal Contribution
Keywordsimage segmentation, segmentation robustness, fuzzy connectedness, watershed transform, image foresting transform, minimum spanning forest, shortest-path forest.
AbstractThis paper analyzes the robustness issue in three segmentation approaches: the iterative relative fuzzy object extraction, the watershed transforms (WT) by image foresting transform and by minimum spanning forest. These methods need input seeds, which can be source of variability in the segmentation result. So, the robustness of these segmentation methods in relation to the input seeds is focused. The core of each seed is defined as the region where the seed can be moved without altering the segmentation result. We demonstrate that the core is identical for the three methods providing that the tie-zone transform has previously been applied on these methods. Indeed, as the two WT approaches do not return unique solution, the set of possible solutions has to be considered in a unified solution. So does the tie-zone transform. As opposed to what we could think, we show that the core is included in but different from the catchment basin. We also demonstrate that the tie-zone transforms of these WTs are always identical. Furthermore, the framework of minimal sets of seeds, an inverse problem of segmentation, is extended to the pixel level and related to the cores. A new algorithm for the computation of minimal seed sets is finally proposed.
source Directory Contentthere are no files
agreement Directory Contentthere are no files
Conditions of access and use area
data URLhttp://urlib.net/rep/sid.inpe.br/sibgrapi@80/2007/07.23.17.55
zipped data URLhttp://urlib.net/zip/sid.inpe.br/sibgrapi@80/2007/07.23.17.55
Languageen
Target Fileaudigier_robust.pdf
User Groupaudigier@dca.fee.unicamp.br
administrator
Visibilityshown
Allied materials area
Mirror Repositorydpi.inpe.br/banon-pc2@80/2006/08.30.19.27
Host Collectionsid.inpe.br/banon/2001/03.30.15.38
Notes area
Empty Fieldsaccessionnumber archivingpolicy archivist area callnumber copyholder copyright creatorhistory descriptionlevel dissemination documentstage doi e-mailaddress edition electronicmailaddress group holdercode isbn issn label lineage mark 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

Close