File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Learning image-specific parameters for interactive segmentation

TitleLearning image-specific parameters for interactive segmentation
Authors
KeywordsApproximation scheme
Conditional random field
Cutting plane methods
Energy margin
Interactive image segmentation
Issue Date2012
PublisherIEEE Computer Society. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000147
Citation
The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI., 16-21 June 2012. In IEEE Conference on Computer Vision and Pattern Recognition Proceedings, 2012, p. 590-597 How to Cite?
Abstract
In this paper, we present a novel interactive image segmentation technique that automatically learns segmentation parameters tailored for each and every image. Unlike existing work, our method does not require any offline parameter tuning or training stage, and is capable of determining image-specific parameters according to some simple user interactions with the target image. We formulate the segmentation problem as an inference of a conditional random field (CRF) over a segmentation mask and the target image, and parametrize this CRF by different weights (e.g., color, texture and smoothing). The weight parameters are learned via an energy margin maximization, which is solved using a constraint approximation scheme and the cutting plane method. Experimental results show that our method, by learning image-specific parameters automatically, outperforms other state-of-the-art interactive image segmentation techniques. © 2012 IEEE.
DescriptionPosters 1B - Color and Texture, Early & Biological Vision, Image Based Modeling, Segmentation and Grouping
Persistent Identifierhttp://hdl.handle.net/10722/152969
ISBN
ISSN
2013 SCImago Journal Rankings: 2.954

 

DC FieldValueLanguage
dc.contributor.authorKuang, Zen_US
dc.contributor.authorSchnieders, Den_US
dc.contributor.authorZhou, Hen_US
dc.contributor.authorWong, KKYen_US
dc.contributor.authorYu, Yen_US
dc.contributor.authorPeng, Ben_US
dc.date.accessioned2012-07-16T09:53:34Z-
dc.date.available2012-07-16T09:53:34Z-
dc.date.issued2012en_US
dc.identifier.citationThe IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI., 16-21 June 2012. In IEEE Conference on Computer Vision and Pattern Recognition Proceedings, 2012, p. 590-597en_US
dc.identifier.isbn978-1-4673-1228-8-
dc.identifier.issn1063-6919-
dc.identifier.urihttp://hdl.handle.net/10722/152969-
dc.descriptionPosters 1B - Color and Texture, Early & Biological Vision, Image Based Modeling, Segmentation and Grouping-
dc.description.abstractIn this paper, we present a novel interactive image segmentation technique that automatically learns segmentation parameters tailored for each and every image. Unlike existing work, our method does not require any offline parameter tuning or training stage, and is capable of determining image-specific parameters according to some simple user interactions with the target image. We formulate the segmentation problem as an inference of a conditional random field (CRF) over a segmentation mask and the target image, and parametrize this CRF by different weights (e.g., color, texture and smoothing). The weight parameters are learned via an energy margin maximization, which is solved using a constraint approximation scheme and the cutting plane method. Experimental results show that our method, by learning image-specific parameters automatically, outperforms other state-of-the-art interactive image segmentation techniques. © 2012 IEEE.-
dc.languageengen_US
dc.publisherIEEE Computer Society. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000147-
dc.relation.ispartofIEEE Conference on Computer Vision and Pattern Recognition Proceedingsen_US
dc.rightsIEEE Conference on Computer Vision and Pattern Recognition. Proceedings. Copyright © IEEE Computer Society.-
dc.rights©2012 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.-
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.subjectApproximation scheme-
dc.subjectConditional random field-
dc.subjectCutting plane methods-
dc.subjectEnergy margin-
dc.subjectInteractive image segmentation-
dc.titleLearning image-specific parameters for interactive segmentationen_US
dc.typeConference_Paperen_US
dc.identifier.emailKuang, Z: kuangzhh@HKUSUC.hku.hken_US
dc.identifier.emailSchnieders, D: scdirk@hku.hken_US
dc.identifier.emailZhou, H: zhhoper@hku.hken_US
dc.identifier.emailWong, KKY: kykwong@cs.hku.hk-
dc.identifier.emailYu, Y: yzyu@cs.hku.hk-
dc.identifier.authorityWong, KKY=rp01393en_US
dc.identifier.authorityYu, Y=rp01415en_US
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1109/CVPR.2012.6247725-
dc.identifier.scopuseid_2-s2.0-84866689544-
dc.identifier.hkuros200763en_US
dc.identifier.spage590-
dc.identifier.epage597-
dc.publisher.placeUnited States-
dc.description.otherThe IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI., 16-21 June 2012. In IEEE Conference on Computer Vision and Pattern Recognition Proceedings, 2012, p. 590-597-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats