dc.creatorMiranda, Paulo A. V.
dc.creatorFalcao, Alexandre Xavier
dc.creatorSpina, Thiago V.
dc.date2012
dc.date2013-09-19T18:06:55Z
dc.date2016-06-30T18:10:12Z
dc.date2013-09-19T18:06:55Z
dc.date2016-06-30T18:10:12Z
dc.date.accessioned2018-03-29T01:52:55Z
dc.date.available2018-03-29T01:52:55Z
dc.identifierIEEE Transactions On Image Processing. IEEE-Inst Electrical Electronics Engineers Inc, v.21, n.6, p.3042-3052, 2012
dc.identifier1057-7149
dc.identifierWOS:000304159800012
dc.identifier10.1109/TIP.2012.2188034
dc.identifierhttp://www.repositorio.unicamp.br/jspui/handle/REPOSIP/2511
dc.identifierhttp://repositorio.unicamp.br/jspui/handle/REPOSIP/2511
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/1308273
dc.descriptionThis paper presents an optimum user-steered boundary tracking approach for image segmentation, which simulates the behavior of water flowing through a riverbed. The riverbed approach was devised using the image foresting transform with a never-exploited connectivity function. We analyze its properties in the derived image graphs and discuss its theoretical relation with other popular methods such as live wire and graph cuts. Several experiments show that riverbed can significantly reduce the number of user interactions (anchor points), as compared to live wire for objects with complex shapes. This paper also includes a discussion about how to combine different methods in order to take advantage of their complementary strengths.
dc.description21
dc.description6
dc.description3042
dc.description3052
dc.descriptionFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
dc.descriptionConselho Nacional de Desenvolvimento Cientiacute
dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
dc.languageeng
dc.publisherIEEE-Inst Electrical Electronics Engineers Inc
dc.publisherPiscataway
dc.relationIEEE Transactions On Image Processing
dc.rightsfechado
dc.sourceWOS
dc.subjectGraph-cut segmentation
dc.subjectgraph search algorithms
dc.subjectimage foresting transform (IFT)
dc.subjectwatershed transform
dc.subjectRELATIVE FUZZY CONNECTEDNESS
dc.subjectLIVE-WIRE SEGMENTATION
dc.subjectACTIVE SHAPE MODELS
dc.subjectINTERACTIVE SEGMENTATION
dc.subjectGRAPH CUTS
dc.subjectALGORITHMS
dc.titleRiverbed: A Novel User-Steered Image Segmentation Method Based on Optimum Boundary Tracking
dc.typeArtículos de revistas


Este ítem pertenece a la siguiente institución