Robust estimation of texture flow via dense feature sampling

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 291
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorTai, Yu-Wing-
dc.contributor.authorBrown, M.S.-
dc.contributor.authorTang, C.-K.-
dc.date.accessioned2013-03-27T23:46:36Z-
dc.date.available2013-03-27T23:46:36Z-
dc.date.created2012-02-06-
dc.date.issued2007-06-
dc.identifier.citationComputer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on, v.0, no.0, pp.1 - 8-
dc.identifier.issn1063-6919-
dc.identifier.urihttp://hdl.handle.net/10203/162353-
dc.description.abstractTexture flow estimation is a valuable step in a variety of vision related tasks, including texture analysis, image segmentation, shape-from-texture and texture remapping. This paper describes a novel and effective technique to estimate texture flow in an image given a small example patch. The key idea consists of extracting a dense set of features from the example patch where discrete orientations are encapsulated into the feature vector such that rotation can be simulated as a linear shift of the vector. This dense feature space is then compressed by PCA and clustered using EM to produce a set of small set of principal features. Obtaining these principal features at varying image scales, we can compute the per-pixel scale and orientation likelihoods for the distorted texture. The final texture flow estimation is formulated as the MAP solution of a labeling Markov network which is solved using belief propagation. Experimental results on both synthetic and real images demonstrate good results even for highly distorted examples.-
dc.languageENG-
dc.publisherIEEE Computer Society-
dc.titleRobust estimation of texture flow via dense feature sampling-
dc.typeConference-
dc.type.rimsCONF-
dc.citation.volume0-
dc.citation.issue0-
dc.citation.beginningpage1-
dc.citation.endingpage8-
dc.citation.publicationnameComputer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on-
dc.identifier.conferencecountryUnited States-
dc.identifier.conferencecountryUnited States-
dc.contributor.localauthorTai, Yu-Wing-
dc.contributor.nonIdAuthorBrown, M.S.-
dc.contributor.nonIdAuthorTang, C.-K.-
Appears in Collection
EE-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0