Show simple item record

dc.contributor.authorXia, Gui-Song
dc.contributor.authorDelon, Julie
HAL ID: 6864
dc.contributor.authorGousseau, Yann
dc.date.accessioned2013-10-14T08:16:26Z
dc.date.available2013-10-14T08:16:26Z
dc.date.issued2012
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/11812
dc.language.isoenen
dc.subjectjunctionsen
dc.subject.ddc518en
dc.titleAn accurate and contrast invariant junction detectoren
dc.typeCommunication / Conférence
dc.description.abstractenThis paper introduces a generic method for the accurate analysis of junctions, relying on a statistical modeling of normalized image gradients. We analyze junctions as local visual events that do not happen by chance under a background model derived from the a-contrario methodology. The method not only provides thresholds for the detection of junctions, but also enables their accurate characterization, including a precise computation of their type, localization, scale and geometrical configuration. The efficiency of the method is evaluated through various experiments.en
dc.identifier.citationpages2780-2783en
dc.relation.ispartoftitle21st International Conference on Pattern Recognition (ICPR), 2012 - proceedingsen
dc.relation.ispartofpublnameIEEEen
dc.relation.ispartofdate2012
dc.subject.ddclabelModèles mathématiques. Algorithmesen
dc.relation.ispartofisbn978-1-4673-2216-4en
dc.relation.conftitle21st International Conference on Pattern Recognition (ICPR), 2012en
dc.relation.confdate2012-11
dc.relation.confcityTsukubaen
dc.relation.confcountryJaponen
dc.relation.forthcomingnonen


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record