FAST LABEL: Easy and efficient solution of joint multi-label and estimation problems

Handle URI:
http://hdl.handle.net/10754/575822
Title:
FAST LABEL: Easy and efficient solution of joint multi-label and estimation problems
Authors:
Sundaramoorthi, Ganesh ( 0000-0003-3471-6384 ) ; Hong, Byungwoo
Abstract:
We derive an easy-to-implement and efficient algorithm for solving multi-label image partitioning problems in the form of the problem addressed by Region Competition. These problems jointly determine a parameter for each of the regions in the partition. Given an estimate of the parameters, a fast approximate solution to the multi-label sub-problem is derived by a global update that uses smoothing and thresholding. The method is empirically validated to be robust to fine details of the image that plague local solutions. Further, in comparison to global methods for the multi-label problem, the method is more efficient and it is easy for a non-specialist to implement. We give sample Matlab code for the multi-label Chan-Vese problem in this paper! Experimental comparison to the state-of-the-art in multi-label solutions to Region Competition shows that our method achieves equal or better accuracy, with the main advantage being speed and ease of implementation.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Electrical Engineering Program; Visual Computing Center (VCC)
Publisher:
Institute of Electrical & Electronics Engineers (IEEE)
Journal:
2014 IEEE Conference on Computer Vision and Pattern Recognition
Conference/Event name:
27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014
Issue Date:
Jun-2014
DOI:
10.1109/CVPR.2014.400
Type:
Conference Paper
ISSN:
10636919
ISBN:
9781479951178; 9781479951178
Appears in Collections:
Conference Papers; Electrical Engineering Program; Electrical Engineering Program; Visual Computing Center (VCC); Visual Computing Center (VCC); Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorSundaramoorthi, Ganeshen
dc.contributor.authorHong, Byungwooen
dc.date.accessioned2015-08-24T09:27:06Zen
dc.date.available2015-08-24T09:27:06Zen
dc.date.issued2014-06en
dc.identifier.isbn9781479951178; 9781479951178en
dc.identifier.issn10636919en
dc.identifier.doi10.1109/CVPR.2014.400en
dc.identifier.urihttp://hdl.handle.net/10754/575822en
dc.description.abstractWe derive an easy-to-implement and efficient algorithm for solving multi-label image partitioning problems in the form of the problem addressed by Region Competition. These problems jointly determine a parameter for each of the regions in the partition. Given an estimate of the parameters, a fast approximate solution to the multi-label sub-problem is derived by a global update that uses smoothing and thresholding. The method is empirically validated to be robust to fine details of the image that plague local solutions. Further, in comparison to global methods for the multi-label problem, the method is more efficient and it is easy for a non-specialist to implement. We give sample Matlab code for the multi-label Chan-Vese problem in this paper! Experimental comparison to the state-of-the-art in multi-label solutions to Region Competition shows that our method achieves equal or better accuracy, with the main advantage being speed and ease of implementation.en
dc.publisherInstitute of Electrical & Electronics Engineers (IEEE)en
dc.subjectMulti-Labelen
dc.subjectSegmentationen
dc.titleFAST LABEL: Easy and efficient solution of joint multi-label and estimation problemsen
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.journal2014 IEEE Conference on Computer Vision and Pattern Recognitionen
dc.conference.date23 June 2014 through 28 June 2014en
dc.conference.name27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014en
dc.contributor.institutionChung-Ang UniversitySeoul, South Koreaen
kaust.authorSundaramoorthi, Ganeshen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.