File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Interactive image segmentation based on level sets of probabilities

TitleInteractive image segmentation based on level sets of probabilities
Authors
KeywordsCurvature
Distance Transform
Image Segmentation
Level Set Method
Statistical Classification
Issue Date2012
PublisherI E E E. The Journal's web site is located at http://www.computer.org/tvcg
Citation
Ieee Transactions On Visualization And Computer Graphics, 2012, v. 18 n. 2, p. 202-213 How to Cite?
Abstract
In this paper, we present a robust and accurate algorithm for interactive image segmentation. The level set method is clearly advantageous for image objects with a complex topology and fragmented appearance. Our method integrates discriminative classification models and distance transforms with the level set method to avoid local minima and better snap to true object boundaries. The level set function approximates a transformed version of pixelwise posterior probabilities of being part of a target object. The evolution of its zero level set is driven by three force terms, region force, edge field force, and curvature force. These forces are based on a probabilistic classifier and an unsigned distance transform of salient edges. We further propose a technique that improves the performance of both the probabilistic classifier and the level set method over multiple passes. It makes the final object segmentation less sensitive to user interactions. Experiments and comparisons demonstrate the effectiveness of our method. © 2012 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/152486
ISSN
2013 Impact Factor: 1.919
2013 SCImago Journal Rankings: 1.402
ISI Accession Number ID
Funding AgencyGrant Number
US National Science Foundation (NSF)IIS 09-14631
Funding Information:

We would like to thank the reviewers, whose comments have been valuable in improving our manuscript. This work was partially supported by US National Science Foundation (NSF) (IIS 09-14631).

References

 

Author Affiliations
  1. University of Electronic Science and Technology of China
  2. University of Illinois at Urbana-Champaign
DC FieldValueLanguage
dc.contributor.authorLiu, Yen_US
dc.contributor.authorYu, Yen_US
dc.date.accessioned2012-06-26T06:39:35Z-
dc.date.available2012-06-26T06:39:35Z-
dc.date.issued2012en_US
dc.identifier.citationIeee Transactions On Visualization And Computer Graphics, 2012, v. 18 n. 2, p. 202-213en_US
dc.identifier.issn1077-2626en_US
dc.identifier.urihttp://hdl.handle.net/10722/152486-
dc.description.abstractIn this paper, we present a robust and accurate algorithm for interactive image segmentation. The level set method is clearly advantageous for image objects with a complex topology and fragmented appearance. Our method integrates discriminative classification models and distance transforms with the level set method to avoid local minima and better snap to true object boundaries. The level set function approximates a transformed version of pixelwise posterior probabilities of being part of a target object. The evolution of its zero level set is driven by three force terms, region force, edge field force, and curvature force. These forces are based on a probabilistic classifier and an unsigned distance transform of salient edges. We further propose a technique that improves the performance of both the probabilistic classifier and the level set method over multiple passes. It makes the final object segmentation less sensitive to user interactions. Experiments and comparisons demonstrate the effectiveness of our method. © 2012 IEEE.en_US
dc.languageengen_US
dc.publisherI E E E. The Journal's web site is located at http://www.computer.org/tvcgen_US
dc.relation.ispartofIEEE Transactions on Visualization and Computer Graphicsen_US
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.subjectCurvatureen_US
dc.subjectDistance Transformen_US
dc.subjectImage Segmentationen_US
dc.subjectLevel Set Methoden_US
dc.subjectStatistical Classificationen_US
dc.titleInteractive image segmentation based on level sets of probabilitiesen_US
dc.typeArticleen_US
dc.identifier.emailYu, Y:yzyu@cs.hku.hken_US
dc.identifier.authorityYu, Y=rp01415en_US
dc.description.naturepublished_or_final_versionen_US
dc.identifier.doi10.1109/TVCG.2011.77en_US
dc.identifier.scopuseid_2-s2.0-83855162158en_US
dc.identifier.hkuros200757-
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-83855162158&selection=ref&src=s&origin=recordpageen_US
dc.identifier.volume18en_US
dc.identifier.issue2en_US
dc.identifier.spage202en_US
dc.identifier.epage213en_US
dc.identifier.isiWOS:000298043100003-
dc.publisher.placeUnited Statesen_US
dc.identifier.scopusauthoridLiu, Y=36844116200en_US
dc.identifier.scopusauthoridYu, Y=8554163500en_US

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats