Coarse-to-Fine Segmentation with Shape-Tailored Continuum Scale Spaces

Handle URI:
http://hdl.handle.net/10754/626947
Title:
Coarse-to-Fine Segmentation with Shape-Tailored Continuum Scale Spaces
Authors:
Khan, Naeemullah; Hong, Byung-Woo; Yezzi, Anthony; Sundaramoorthi, Ganesh ( 0000-0003-3471-6384 )
Abstract:
We formulate an energy for segmentation that is designed to have preference for segmenting the coarse over fine structure of the image, without smoothing across boundaries of regions. The energy is formulated by integrating a continuum of scales from a scale space computed from the heat equation within regions. We show that the energy can be optimized without computing a continuum of scales, but instead from a single scale. This makes the method computationally efficient in comparison to energies using a discrete set of scales. We apply our method to texture and motion segmentation. Experiments on benchmark datasets show that a continuum of scales leads to better segmentation accuracy over discrete scales and other competing methods.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Electrical Engineering Program; Visual Computing Center (VCC)
Citation:
Khan N, Hong B-W, Yezzi A, Sundaramoorthi G (2017) Coarse-to-Fine Segmentation with Shape-Tailored Continuum Scale Spaces. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Available: http://dx.doi.org/10.1109/CVPR.2017.188.
Publisher:
IEEE
Journal:
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
KAUST Grant Number:
OCRF-2014-CRG3-62140401
Conference/Event name:
30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Issue Date:
9-Nov-2017
DOI:
10.1109/CVPR.2017.188
Type:
Conference Paper
Sponsors:
Partially funded by KAUST OCRF-2014-CRG3-62140401, NRF-2014R1A2A1A11051941, and NSF CCF-1526848.
Additional Links:
http://ieeexplore.ieee.org/document/8099671/; http://openaccess.thecvf.com/content_cvpr_2017/html/Khan_Coarse-To-Fine_Segmentation_With_CVPR_2017_paper.html
Appears in Collections:
Conference Papers; Electrical Engineering Program; Visual Computing Center (VCC); Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorKhan, Naeemullahen
dc.contributor.authorHong, Byung-Wooen
dc.contributor.authorYezzi, Anthonyen
dc.contributor.authorSundaramoorthi, Ganeshen
dc.date.accessioned2018-01-29T12:09:30Z-
dc.date.available2018-01-29T12:09:30Z-
dc.date.issued2017-11-09en
dc.identifier.citationKhan N, Hong B-W, Yezzi A, Sundaramoorthi G (2017) Coarse-to-Fine Segmentation with Shape-Tailored Continuum Scale Spaces. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Available: http://dx.doi.org/10.1109/CVPR.2017.188.en
dc.identifier.doi10.1109/CVPR.2017.188en
dc.identifier.urihttp://hdl.handle.net/10754/626947-
dc.description.abstractWe formulate an energy for segmentation that is designed to have preference for segmenting the coarse over fine structure of the image, without smoothing across boundaries of regions. The energy is formulated by integrating a continuum of scales from a scale space computed from the heat equation within regions. We show that the energy can be optimized without computing a continuum of scales, but instead from a single scale. This makes the method computationally efficient in comparison to energies using a discrete set of scales. We apply our method to texture and motion segmentation. Experiments on benchmark datasets show that a continuum of scales leads to better segmentation accuracy over discrete scales and other competing methods.en
dc.description.sponsorshipPartially funded by KAUST OCRF-2014-CRG3-62140401, NRF-2014R1A2A1A11051941, and NSF CCF-1526848.en
dc.publisherIEEEen
dc.relation.urlhttp://ieeexplore.ieee.org/document/8099671/en
dc.relation.urlhttp://openaccess.thecvf.com/content_cvpr_2017/html/Khan_Coarse-To-Fine_Segmentation_With_CVPR_2017_paper.html-
dc.rights(c) 2017 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.titleCoarse-to-Fine Segmentation with Shape-Tailored Continuum Scale Spacesen
dc.typeConference Paperen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentElectrical Engineering Programen
dc.contributor.departmentVisual Computing Center (VCC)en
dc.identifier.journal2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)en
dc.conference.dateJUL 21-26, 2017en
dc.conference.name30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)en
dc.conference.locationHonolulu, HIen
dc.eprint.versionPost-printen
dc.contributor.institutionChung-Ang University, Koreaen
dc.contributor.institutionGeorgia Tech, USAen
kaust.authorKhan, Naeemullahen
kaust.authorSundaramoorthi, Ganeshen
kaust.grant.numberOCRF-2014-CRG3-62140401en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.