Show simple item record

dc.contributor.authorSu, Sara L.
dc.contributor.authorDurand, Frédo
dc.contributor.authorAgrawala, Maneesh
dc.date.accessioned2005-12-14T19:02:18Z
dc.date.available2005-12-14T19:02:18Z
dc.date.issued2006-01
dc.identifier.urihttp://hdl.handle.net/1721.1/30220
dc.description.abstractWe present a post-processing technique that selectively reduces the salience of distracting regions in an image. Computational models of attention predict that texture variation influences bottom-up attention mechanisms. Our method reduces the spatial variation of texture using power maps, high-order features describing local frequency content in an image. Modification of power maps results in effective regional de-emphasis. We validate our results quantitatively via a human subject search experiment and qualitatively with eye tracking data.en
dc.description.sponsorshipSingapore-MIT Alliance (SMA)en
dc.format.extent9465431 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoenen
dc.relation.ispartofseriesComputer Science (CS)en
dc.subjectImage processingen
dc.subjectcomputational photographyen
dc.subjectsaliencyen
dc.subjectvisual attentionen
dc.subjectpower mapen
dc.titleDe-Emphasis of Distracting Image Regions Using Texture Power Mapsen
dc.typeArticleen


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record