Show simple item record

dc.contributor.authorKhan, Naeemullah
dc.contributor.authorAlgarni, Marei Saeed Mohammed
dc.contributor.authorYezzi, Anthony
dc.contributor.authorSundaramoorthi, Ganesh
dc.date.accessioned2015-10-21T13:24:48Z
dc.date.available2015-10-21T13:24:48Z
dc.date.issued2015-10-15
dc.identifier.citationKhan, Naeemullah, Marei Algarni, Anthony Yezzi, and Ganesh Sundaramoorthi. "Shape-Tailored Local Descriptors and their Application to Segmentation and Tracking." In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3890-3899. 2015
dc.identifier.doi10.1109/CVPR.2015.7299014
dc.identifier.urihttp://hdl.handle.net/10754/580029
dc.description.abstractWe propose new dense descriptors for texture segmentation. Given a region of arbitrary shape in an image, these descriptors are formed from shape-dependent scale spaces of oriented gradients. These scale spaces are defined by Poisson-like partial differential equations. A key property of our new descriptors is that they do not aggregate image data across the boundary of the region, in contrast to existing descriptors based on aggregation of oriented gradients. As an example, we show how the descriptor can be incorporated in a Mumford-Shah energy for texture segmentation. We test our method on several challenging datasets for texture segmentation and textured object tracking. Experiments indicate that our descriptors lead to more accurate segmentation than non-shape dependent descriptors and the state-of-the-art in texture segmentation.
dc.language.isoen
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.relation.urlhttp://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7299014
dc.rights(c) 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.
dc.titleShape-tailored local descriptors and their application to segmentation and tracking
dc.typeConference Paper
dc.contributor.departmentComputer Science Program
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentElectrical Engineering Program
dc.contributor.departmentVisual Computing Center (VCC)
dc.identifier.journal2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
dc.conference.date2015-06-07 to 2015-06-12
dc.conference.nameIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
dc.conference.locationBoston, MA, USA
dc.eprint.versionPost-print
dc.contributor.institutionSchool of Electrical & Computer Engineering, Georgia Institute of Technology, USA
dc.contributor.affiliationKing Abdullah University of Science and Technology (KAUST)
kaust.personKhan, Naeemullah
kaust.personAlgarni, Marei Saeed Mohammed
kaust.personSundaramoorthi, Ganesh
refterms.dateFOA2018-06-14T09:21:50Z
dc.date.published-online2015-10-15
dc.date.published-print2015-06


Files in this item

Thumbnail
Name:
Khan_Shape-Tailored_Local_Descriptors_2015_CVPR_paper.pdf
Size:
7.234Mb
Format:
PDF
Description:
Accepted Manuscript

This item appears in the following Collection(s)

Show simple item record