Automatic Parametrisation for an image completion method based on markov random fields

Huy Tho Ho, Roland Goecke

Research output: A Conference proceeding or a Chapter in BookConference contribution

4 Citations (Scopus)

Abstract

Recently, a new exemplar-based method for image completion, texture synthesis and image inpainting was proposed which uses a discrete global optimization strategy based on Markov random fields. Its main advantage lies in the use of priority belief propagation and dynamic label pruning to reduce the computational cost of standard belief propagation while producing high quality results. However, one of the drawbacks of the method is its use of a heuristically chosen parameter set. In this paper, a method for automatically determining the parameters for the belief propagation and dynamic label pruning steps is presented. The method is based on an information theoretic approach making use of the entropy of the image patches and the distribution of pairwise node potentials. A number of image completion results are shown demonstrating the effectiveness of our method.
Original languageEnglish
Title of host publicationProceedings of the 2007 IEEE International Conference on Image Processing ICIP2007
Place of PublicationAustralia
PublisherIEEE
Pages541-544
Number of pages4
ISBN (Print)1-4244-1437-7
DOIs
Publication statusPublished - 2007
Externally publishedYes
EventICIP2007 - San Antonio, United States
Duration: 16 Sep 200719 Sep 2007

Conference

ConferenceICIP2007
CountryUnited States
CitySan Antonio
Period16/09/0719/09/07

Fingerprint Dive into the research topics of 'Automatic Parametrisation for an image completion method based on markov random fields'. Together they form a unique fingerprint.

  • Cite this

    Ho, H. T., & Goecke, R. (2007). Automatic Parametrisation for an image completion method based on markov random fields. In Proceedings of the 2007 IEEE International Conference on Image Processing ICIP2007 (pp. 541-544). IEEE. https://doi.org/10.1109/ICIP.2007.4379366