A new model and simple algorithms for multi-label mumford-shah problems

Handle URI:
http://hdl.handle.net/10754/564741
Title:
A new model and simple algorithms for multi-label mumford-shah problems
Authors:
Hong, Byungwoo; Lu, Zhaojin ( 0000-0003-1429-5033 ) ; Sundaramoorthi, Ganesh ( 0000-0003-3471-6384 )
Abstract:
In this work, we address the multi-label Mumford-Shah problem, i.e., the problem of jointly estimating a partitioning of the domain of the image, and functions defined within regions of the partition. We create algorithms that are efficient, robust to undesirable local minima, and are easy-to-implement. Our algorithms are formulated by slightly modifying the underlying statistical model from which the multi-label Mumford-Shah functional is derived. The advantage of this statistical model is that the underlying variables: the labels and the functions are less coupled than in the original formulation, and the labels can be computed from the functions with more global updates. The resulting algorithms can be tuned to the desired level of locality of the solution: from fully global updates to more local updates. We demonstrate our algorithm on two applications: joint multi-label segmentation and denoising, and joint multi-label motion segmentation and flow estimation. We compare to the state-of-the-art in multi-label Mumford-Shah problems and show that we achieve more promising results. © 2013 IEEE.
KAUST Department:
Electrical Engineering Program; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Visual Computing Center (VCC)
Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
Journal:
2013 IEEE Conference on Computer Vision and Pattern Recognition
Conference/Event name:
26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2013
Issue Date:
Jun-2013
DOI:
10.1109/CVPR.2013.161
Type:
Conference Paper
ISSN:
10636919
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.authorHong, Byungwooen
dc.contributor.authorLu, Zhaojinen
dc.contributor.authorSundaramoorthi, Ganeshen
dc.date.accessioned2015-08-04T07:14:23Zen
dc.date.available2015-08-04T07:14:23Zen
dc.date.issued2013-06en
dc.identifier.issn10636919en
dc.identifier.doi10.1109/CVPR.2013.161en
dc.identifier.urihttp://hdl.handle.net/10754/564741en
dc.description.abstractIn this work, we address the multi-label Mumford-Shah problem, i.e., the problem of jointly estimating a partitioning of the domain of the image, and functions defined within regions of the partition. We create algorithms that are efficient, robust to undesirable local minima, and are easy-to-implement. Our algorithms are formulated by slightly modifying the underlying statistical model from which the multi-label Mumford-Shah functional is derived. The advantage of this statistical model is that the underlying variables: the labels and the functions are less coupled than in the original formulation, and the labels can be computed from the functions with more global updates. The resulting algorithms can be tuned to the desired level of locality of the solution: from fully global updates to more local updates. We demonstrate our algorithm on two applications: joint multi-label segmentation and denoising, and joint multi-label motion segmentation and flow estimation. We compare to the state-of-the-art in multi-label Mumford-Shah problems and show that we achieve more promising results. © 2013 IEEE.en
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.subjectjoint estimation problemsen
dc.subjectlevel setsen
dc.subjectMumford-Shahen
dc.subjectPDE methodsen
dc.subjectsegmentationen
dc.titleA new model and simple algorithms for multi-label mumford-shah problemsen
dc.typeConference Paperen
dc.contributor.departmentElectrical Engineering Programen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentVisual Computing Center (VCC)en
dc.identifier.journal2013 IEEE Conference on Computer Vision and Pattern Recognitionen
dc.conference.date23 June 2013 through 28 June 2013en
dc.conference.name26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2013en
dc.conference.locationPortland, ORen
dc.contributor.institutionChung-Ang University, South Koreaen
kaust.authorLu, Zhaojinen
kaust.authorSundaramoorthi, Ganeshen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.