Shape-tailored local descriptors and their application to segmentation and tracking

Handle URI:
http://hdl.handle.net/10754/580029
Title:
Shape-tailored local descriptors and their application to segmentation and tracking
Authors:
Khan, Naeemullah; Algarni, Marei; Yezzi, Anthony; Sundaramoorthi, Ganesh ( 0000-0003-3471-6384 )
Abstract:
We 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.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Citation:
Khan, 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
Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
Journal:
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Conference/Event name:
IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
Issue Date:
7-Jun-2015
DOI:
10.1109/CVPR.2015.7299014
Type:
Conference Paper
Additional Links:
http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7299014
Appears in Collections:
Conference Papers; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorKhan, Naeemullahen
dc.contributor.authorAlgarni, Mareien
dc.contributor.authorYezzi, Anthonyen
dc.contributor.authorSundaramoorthi, Ganeshen
dc.date.accessioned2015-10-21T13:24:48Zen
dc.date.available2015-10-21T13:24:48Zen
dc.date.issued2015-06-07en
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. 2015en
dc.identifier.doi10.1109/CVPR.2015.7299014en
dc.identifier.urihttp://hdl.handle.net/10754/580029en
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.en
dc.language.isoenen
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.relation.urlhttp://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7299014en
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.en
dc.titleShape-tailored local descriptors and their application to segmentation and trackingen
dc.typeConference Paperen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.identifier.journal2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)en
dc.conference.date2015-06-07 to 2015-06-12en
dc.conference.nameIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015en
dc.conference.locationBoston, MA, USAen
dc.eprint.versionPost-printen
dc.contributor.institutionSchool of Electrical & Computer Engineering, Georgia Institute of Technology, USAen
dc.contributor.affiliationKing Abdullah University of Science and Technology (KAUST)en
kaust.authorKhan, Naeemullahen
kaust.authorAlgarni, Mareien
kaust.authorSundaramoorthi, Ganeshen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.