File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

postgraduate thesis: An efficient algorithm for face sketch synthesis using Markov weight fields and cascade decomposition method

TitleAn efficient algorithm for face sketch synthesis using Markov weight fields and cascade decomposition method
Authors
Advisors
Advisor(s):Wong, KKY
Issue Date2012
PublisherThe University of Hong Kong (Pokfulam, Hong Kong)
Citation
Zhou, H. [周浩]. (2012). An efficient algorithm for face sketch synthesis using Markov weight fields and cascade decomposition method. (Thesis). University of Hong Kong, Pokfulam, Hong Kong SAR. Retrieved from http://dx.doi.org/10.5353/th_b4961805
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 thesis, a novel Markov Weight Fields (MWF) model is proposed. By applying linear combination of candidate patches, MWF is capable of synthesizing new sketch patches. The MWF model can be formulated into a convex quadratic programming (QP) problem to which the optimal solution is guaranteed. Based on the Markov property of MWF model, a cascade decomposition method (CDM) is further proposed for solving such a large scale QP problem efficiently. Experiments show that the proposed CDM is very efficient, and only takes about 2:4 seconds. To deal with illumination changes of input photos, five special shading patches are included as candidate patches in addition to the patches selected from the training data. These patches help keeping structure of the face under different illumination conditions as well as synthesize shadows similar to the input photos. Extensive experiments on the CUHK face sketch database, AR database and Chinese celebrity photos show that the proposed model outperforms the common MRF model used in other state-of-the-art methods and is robust to illumination changes.
DegreeMaster of Philosophy
SubjectHuman face recognition (Computer science) - Mathematical models.
Markov random fields.
Dept/ProgramComputer Science
Persistent Identifierhttp://hdl.handle.net/10722/180984

 

DC FieldValueLanguage
dc.contributor.advisorWong, KKY-
dc.contributor.authorZhou, Hao-
dc.contributor.author周浩-
dc.date.accessioned2013-02-07T06:22:01Z-
dc.date.available2013-02-07T06:22:01Z-
dc.date.issued2012-
dc.identifier.citationZhou, H. [周浩]. (2012). An efficient algorithm for face sketch synthesis using Markov weight fields and cascade decomposition method. (Thesis). University of Hong Kong, Pokfulam, Hong Kong SAR. Retrieved from http://dx.doi.org/10.5353/th_b4961805-
dc.identifier.urihttp://hdl.handle.net/10722/180984-
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 thesis, a novel Markov Weight Fields (MWF) model is proposed. By applying linear combination of candidate patches, MWF is capable of synthesizing new sketch patches. The MWF model can be formulated into a convex quadratic programming (QP) problem to which the optimal solution is guaranteed. Based on the Markov property of MWF model, a cascade decomposition method (CDM) is further proposed for solving such a large scale QP problem efficiently. Experiments show that the proposed CDM is very efficient, and only takes about 2:4 seconds. To deal with illumination changes of input photos, five special shading patches are included as candidate patches in addition to the patches selected from the training data. These patches help keeping structure of the face under different illumination conditions as well as synthesize shadows similar to the input photos. Extensive experiments on the CUHK face sketch database, AR database and Chinese celebrity photos show that the proposed model outperforms the common MRF model used in other state-of-the-art methods and is robust to illumination changes.-
dc.languageeng-
dc.publisherThe University of Hong Kong (Pokfulam, Hong Kong)-
dc.relation.ispartofHKU Theses Online (HKUTO)-
dc.rightsThe author retains all proprietary rights, (such as patent rights) and the right to use in future works.-
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.source.urihttp://hub.hku.hk/bib/B49618052-
dc.subject.lcshHuman face recognition (Computer science) - Mathematical models.-
dc.subject.lcshMarkov random fields.-
dc.titleAn efficient algorithm for face sketch synthesis using Markov weight fields and cascade decomposition method-
dc.typePG_Thesis-
dc.identifier.hkulb4961805-
dc.description.thesisnameMaster of Philosophy-
dc.description.thesislevelMaster-
dc.description.thesisdisciplineComputer Science-
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.5353/th_b4961805-
dc.date.hkucongregation2013-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats