File Download
 
Links for fulltext
(May Require Subscription)
 
Supplementary

Conference Paper: Markov Weight Fields for face sketch synthesis
  • Basic View
  • Metadata View
  • XML View
TitleMarkov Weight Fields for face sketch synthesis
 
AuthorsZhou, H1
Kuang, Z1
Wong, KKY1
 
KeywordsConvex quadratic programming
Decomposition methods
Face sketch synthesis
Markov property
Markov random fields models
 
Issue Date2012
 
PublisherIEEE Computer Society. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000147
 
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. 1091-1097 [How to Cite?]
DOI: http://dx.doi.org/10.1109/CVPR.2012.6247788
 
AbstractGreat progress has been made in face sketch synthesis in recent years. State-of-the-art methods commonly apply a Markov Random Fields (MRF) model to select local sketch patches from a set of training data. Such methods, however, have two major drawbacks. Firstly, the MRF model used cannot synthesize new sketch patches. Secondly, the optimization problem in solving the MRF is NP-hard. In this paper, we propose a novel Markov Weight Fields (MWF) model that is capable of synthesizing new sketch patches. We formulate our model into a convex quadratic programming (QP) problem to which the optimal solution is guaranteed. Based on the Markov property of our model, we further propose a cascade decomposition method (CDM) for solving such a large scale QP problem efficiently. Experimental results on the CUHK face sketch database and celebrity photos show that our model outperforms the common MRF model used in other state-of-the-art methods. © 2012 IEEE.
 
DescriptionPosters 1C - Vision for Graphics, Sensors, Medical, Vision for Robotics, Applications
 
ISBN978-1-4673-1228-8
 
ISSN1063-6919
2013 SCImago Journal Rankings: 2.954
 
DOIhttp://dx.doi.org/10.1109/CVPR.2012.6247788
 
DC FieldValue
dc.contributor.authorZhou, H
 
dc.contributor.authorKuang, Z
 
dc.contributor.authorWong, KKY
 
dc.date.accessioned2012-08-16T06:03:10Z
 
dc.date.available2012-08-16T06:03:10Z
 
dc.date.issued2012
 
dc.description.abstractGreat progress has been made in face sketch synthesis in recent years. State-of-the-art methods commonly apply a Markov Random Fields (MRF) model to select local sketch patches from a set of training data. Such methods, however, have two major drawbacks. Firstly, the MRF model used cannot synthesize new sketch patches. Secondly, the optimization problem in solving the MRF is NP-hard. In this paper, we propose a novel Markov Weight Fields (MWF) model that is capable of synthesizing new sketch patches. We formulate our model into a convex quadratic programming (QP) problem to which the optimal solution is guaranteed. Based on the Markov property of our model, we further propose a cascade decomposition method (CDM) for solving such a large scale QP problem efficiently. Experimental results on the CUHK face sketch database and celebrity photos show that our model outperforms the common MRF model used in other state-of-the-art methods. © 2012 IEEE.
 
dc.description.naturepublished_or_final_version
 
dc.descriptionPosters 1C - Vision for Graphics, Sensors, Medical, Vision for Robotics, Applications
 
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. 1091-1097
 
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. 1091-1097 [How to Cite?]
DOI: http://dx.doi.org/10.1109/CVPR.2012.6247788
 
dc.identifier.doihttp://dx.doi.org/10.1109/CVPR.2012.6247788
 
dc.identifier.epage1097
 
dc.identifier.hkuros203486
 
dc.identifier.isbn978-1-4673-1228-8
 
dc.identifier.issn1063-6919
2013 SCImago Journal Rankings: 2.954
 
dc.identifier.scopuseid_2-s2.0-84866686477
 
dc.identifier.spage1091
 
dc.identifier.urihttp://hdl.handle.net/10722/160098
 
dc.languageeng
 
dc.publisherIEEE Computer Society. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000147
 
dc.publisher.placeUnited States
 
dc.relation.ispartofIEEE Conference on Computer Vision and Pattern Recognition Proceedings
 
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.subjectConvex quadratic programming
 
dc.subjectDecomposition methods
 
dc.subjectFace sketch synthesis
 
dc.subjectMarkov property
 
dc.subjectMarkov random fields models
 
dc.titleMarkov Weight Fields for face sketch synthesis
 
dc.typeConference_Paper
 
<?xml encoding="utf-8" version="1.0"?>
<item><contributor.author>Zhou, H</contributor.author>
<contributor.author>Kuang, Z</contributor.author>
<contributor.author>Wong, KKY</contributor.author>
<date.accessioned>2012-08-16T06:03:10Z</date.accessioned>
<date.available>2012-08-16T06:03:10Z</date.available>
<date.issued>2012</date.issued>
<identifier.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. 1091-1097</identifier.citation>
<identifier.isbn>978-1-4673-1228-8</identifier.isbn>
<identifier.issn>1063-6919</identifier.issn>
<identifier.uri>http://hdl.handle.net/10722/160098</identifier.uri>
<description>Posters 1C - Vision for Graphics, Sensors, Medical, Vision for Robotics, Applications</description>
<description.abstract>Great progress has been made in face sketch synthesis in recent years. State-of-the-art methods commonly apply a Markov Random Fields (MRF) model to select local sketch patches from a set of training data. Such methods, however, have two major drawbacks. Firstly, the MRF model used cannot synthesize new sketch patches. Secondly, the optimization problem in solving the MRF is NP-hard. In this paper, we propose a novel Markov Weight Fields (MWF) model that is capable of synthesizing new sketch patches. We formulate our model into a convex quadratic programming (QP) problem to which the optimal solution is guaranteed. Based on the Markov property of our model, we further propose a cascade decomposition method (CDM) for solving such a large scale QP problem efficiently. Experimental results on the CUHK face sketch database and celebrity photos show that our model outperforms the common MRF model used in other state-of-the-art methods. &#169; 2012 IEEE.</description.abstract>
<language>eng</language>
<publisher>IEEE Computer Society. The Journal&apos;s web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000147</publisher>
<relation.ispartof>IEEE Conference on Computer Vision and Pattern Recognition Proceedings</relation.ispartof>
<rights>IEEE Conference on Computer Vision and Pattern Recognition. Proceedings. Copyright &#169; IEEE Computer Society.</rights>
<rights>&#169;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.</rights>
<rights>Creative Commons: Attribution 3.0 Hong Kong License</rights>
<subject>Convex quadratic programming</subject>
<subject>Decomposition methods</subject>
<subject>Face sketch synthesis</subject>
<subject>Markov property</subject>
<subject>Markov random fields models</subject>
<title>Markov Weight Fields for face sketch synthesis</title>
<type>Conference_Paper</type>
<description.nature>published_or_final_version</description.nature>
<identifier.doi>10.1109/CVPR.2012.6247788</identifier.doi>
<identifier.scopus>eid_2-s2.0-84866686477</identifier.scopus>
<identifier.hkuros>203486</identifier.hkuros>
<identifier.spage>1091</identifier.spage>
<identifier.epage>1097</identifier.epage>
<publisher.place>United States</publisher.place>
<description.other>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. 1091-1097</description.other>
<bitstream.url>http://hub.hku.hk/bitstream/10722/160098/1/Content.pdf</bitstream.url>
</item>
Author Affiliations
  1. The University of Hong Kong