Show simple item record

dc.contributor.authorCaselles, Vincent
dc.contributor.authorColl, Bartomeu
dc.contributor.authorMorel, Jean-Michel
dc.date.accessioned2011-07-15T12:05:11Z
dc.date.available2011-07-15T12:05:11Z
dc.date.issued1997
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/6695
dc.language.isoenen
dc.subjectScale Space theoriesen
dc.subjectimagesen
dc.subject.ddc519en
dc.titleScale space versus topographic map for natural imagesen
dc.typeCommunication / Conférence
dc.description.abstractenWe call "natural" image any photograph of an outdoor or indoor scene taken by a standard camera. In such images, most observed objects undergo occlusions and the illumination condition and contrast response of the camera are unknown. Actual Scale Space theories do not incorporate obvious restrictions imposed by the physics of image generation. The heat equation (linear scale space) is not contrast invariant and destroys T-junctions. The same is true for the recently proposed curvature equations (mean curvature motion and affine shortening): They break the symmetry of junctions. To apply directly these models to natural world images, with occlusions, is irrevelant. Returning to the edge detection problem, in which scale space theory originates, we show how level lines can be found in an image without smoothing. As an alternative to edge detection/scale space, we propose to define the line structure in a natural image by its topographic map (set of all level lines). We also show that a modification of morphological scale space can help to the visualization of the topographic map.en
dc.identifier.citationpages29-49en
dc.relation.ispartofseriestitleLecture Notes in Computer Science
dc.relation.ispartofseriesnumber1252
dc.relation.ispartoftitleScale-Space Theory in Computer Vision First International Conference, Scale-Space'97 Utrecht, The Netherlands, July 2–4, 1997 Proceedingsen
dc.relation.ispartofeditorHaar Romeny, Bart ter
dc.relation.ispartofeditorFlorack, Luc
dc.relation.ispartofeditorKoenderink, Jan
dc.relation.ispartofeditorViergever, Max
dc.relation.ispartofpublnameSpringeren
dc.relation.ispartofpublcityBerlinen
dc.relation.ispartofdate1997
dc.relation.ispartofpages365en
dc.relation.ispartofurlhttp://dx.doi.org/10.1007/3-540-63167-4en
dc.description.sponsorshipprivateouien
dc.subject.ddclabelProbabilités et mathématiques appliquéesen
dc.relation.ispartofisbn978-3-540-63167-5en
dc.relation.conftitleFirst International Conference on Scale-Space Theory in Computer Vision (Scale-Space'97)en
dc.relation.confdate1997-07
dc.relation.confcityUtrechten
dc.relation.confcountryPays-Basen
dc.identifier.doihttp://dx.doi.org/10.1007/3-540-63167-4_38


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record