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

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

Labels
Global optimization
Entropy
Textures
Costs

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). Australia: IEEE. https://doi.org/10.1109/ICIP.2007.4379366
Ho, Huy Tho ; Goecke, Roland. / Automatic Parametrisation for an image completion method based on markov random fields. Proceedings of the 2007 IEEE International Conference on Image Processing ICIP2007. Australia : IEEE, 2007. pp. 541-544
@inproceedings{a50a652672804b54832f797094c4da8a,
title = "Automatic Parametrisation for an image completion method based on markov random fields",
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.",
author = "Ho, {Huy Tho} and Roland Goecke",
year = "2007",
doi = "10.1109/ICIP.2007.4379366",
language = "English",
isbn = "1-4244-1437-7",
pages = "541--544",
booktitle = "Proceedings of the 2007 IEEE International Conference on Image Processing ICIP2007",
publisher = "IEEE",

}

Ho, HT & 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. IEEE, Australia, pp. 541-544, ICIP2007, San Antonio, United States, 16/09/07. https://doi.org/10.1109/ICIP.2007.4379366

Automatic Parametrisation for an image completion method based on markov random fields. / Ho, Huy Tho; Goecke, Roland.

Proceedings of the 2007 IEEE International Conference on Image Processing ICIP2007. Australia : IEEE, 2007. p. 541-544.

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

TY - GEN

T1 - Automatic Parametrisation for an image completion method based on markov random fields

AU - Ho, Huy Tho

AU - Goecke, Roland

PY - 2007

Y1 - 2007

N2 - 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.

AB - 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.

U2 - 10.1109/ICIP.2007.4379366

DO - 10.1109/ICIP.2007.4379366

M3 - Conference contribution

SN - 1-4244-1437-7

SP - 541

EP - 544

BT - Proceedings of the 2007 IEEE International Conference on Image Processing ICIP2007

PB - IEEE

CY - Australia

ER -

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