Bayesian region selection for adaptive dictionary-based super-resolution

Research output: Contribution to conferencePaperResearchpeer review

Authors

  • Eduardo Pérez-Pellitero
  • Jordi Salvador
  • Javier Ruiz-Hidalgo
  • Bodo Rosenhahn

External Research Organisations

  • Universitat Politècnica de Catalunya
  • Technicolor Research & Innovation
View graph of relations

Details

Original languageEnglish
Publication statusPublished - 2013
Event2013 24th British Machine Vision Conference, BMVC 2013 - Bristol, United Kingdom (UK)
Duration: 9 Sept 201313 Sept 2013

Conference

Conference2013 24th British Machine Vision Conference, BMVC 2013
Country/TerritoryUnited Kingdom (UK)
CityBristol
Period9 Sept 201313 Sept 2013

Abstract

The performance of dictionary-based super-resolution (SR) strongly depends on the contents of the training dataset. Nevertheless, many dictionary-based SR methods randomly select patches from of a larger set of training images to build their dictionaries [8, 14, 19, 20], thus relying on patches being diverse enough. This paper describes a dictionary building method for SR based on adaptively selecting an optimal subset of patches out of the training images. Each training image is divided into sub-image entities, named regions, of such a size that texture consistency is preserved and high-frequency (HF) energy is present. For each input patch to super-resolve, the best-fitting region is found through a Bayesian selection. In order to handle the high number of regions in the training dataset, a local Naive Bayes Nearest Neighbor (NBNN) approach is used. Trained with this adapted subset of patches, sparse coding SR is applied to recover the high-resolution image. Experimental results demonstrate that using our adaptive algorithm produces an improvement in SR performance with respect to non-adaptive training.

ASJC Scopus subject areas

Cite this

Bayesian region selection for adaptive dictionary-based super-resolution. / Pérez-Pellitero, Eduardo; Salvador, Jordi; Ruiz-Hidalgo, Javier et al.
2013. Paper presented at 2013 24th British Machine Vision Conference, BMVC 2013, Bristol, United Kingdom (UK).

Research output: Contribution to conferencePaperResearchpeer review

Pérez-Pellitero, E, Salvador, J, Ruiz-Hidalgo, J & Rosenhahn, B 2013, 'Bayesian region selection for adaptive dictionary-based super-resolution', Paper presented at 2013 24th British Machine Vision Conference, BMVC 2013, Bristol, United Kingdom (UK), 9 Sept 2013 - 13 Sept 2013. https://doi.org/10.5244/C.27.37
Pérez-Pellitero, E., Salvador, J., Ruiz-Hidalgo, J., & Rosenhahn, B. (2013). Bayesian region selection for adaptive dictionary-based super-resolution. Paper presented at 2013 24th British Machine Vision Conference, BMVC 2013, Bristol, United Kingdom (UK). https://doi.org/10.5244/C.27.37
Pérez-Pellitero E, Salvador J, Ruiz-Hidalgo J, Rosenhahn B. Bayesian region selection for adaptive dictionary-based super-resolution. 2013. Paper presented at 2013 24th British Machine Vision Conference, BMVC 2013, Bristol, United Kingdom (UK). doi: 10.5244/C.27.37
Pérez-Pellitero, Eduardo ; Salvador, Jordi ; Ruiz-Hidalgo, Javier et al. / Bayesian region selection for adaptive dictionary-based super-resolution. Paper presented at 2013 24th British Machine Vision Conference, BMVC 2013, Bristol, United Kingdom (UK).
Download
@conference{c4b187a61dc9420d848a6483adb0a283,
title = "Bayesian region selection for adaptive dictionary-based super-resolution",
abstract = "The performance of dictionary-based super-resolution (SR) strongly depends on the contents of the training dataset. Nevertheless, many dictionary-based SR methods randomly select patches from of a larger set of training images to build their dictionaries [8, 14, 19, 20], thus relying on patches being diverse enough. This paper describes a dictionary building method for SR based on adaptively selecting an optimal subset of patches out of the training images. Each training image is divided into sub-image entities, named regions, of such a size that texture consistency is preserved and high-frequency (HF) energy is present. For each input patch to super-resolve, the best-fitting region is found through a Bayesian selection. In order to handle the high number of regions in the training dataset, a local Naive Bayes Nearest Neighbor (NBNN) approach is used. Trained with this adapted subset of patches, sparse coding SR is applied to recover the high-resolution image. Experimental results demonstrate that using our adaptive algorithm produces an improvement in SR performance with respect to non-adaptive training.",
author = "Eduardo P{\'e}rez-Pellitero and Jordi Salvador and Javier Ruiz-Hidalgo and Bodo Rosenhahn",
year = "2013",
doi = "10.5244/C.27.37",
language = "English",
note = "2013 24th British Machine Vision Conference, BMVC 2013 ; Conference date: 09-09-2013 Through 13-09-2013",

}

Download

TY - CONF

T1 - Bayesian region selection for adaptive dictionary-based super-resolution

AU - Pérez-Pellitero, Eduardo

AU - Salvador, Jordi

AU - Ruiz-Hidalgo, Javier

AU - Rosenhahn, Bodo

PY - 2013

Y1 - 2013

N2 - The performance of dictionary-based super-resolution (SR) strongly depends on the contents of the training dataset. Nevertheless, many dictionary-based SR methods randomly select patches from of a larger set of training images to build their dictionaries [8, 14, 19, 20], thus relying on patches being diverse enough. This paper describes a dictionary building method for SR based on adaptively selecting an optimal subset of patches out of the training images. Each training image is divided into sub-image entities, named regions, of such a size that texture consistency is preserved and high-frequency (HF) energy is present. For each input patch to super-resolve, the best-fitting region is found through a Bayesian selection. In order to handle the high number of regions in the training dataset, a local Naive Bayes Nearest Neighbor (NBNN) approach is used. Trained with this adapted subset of patches, sparse coding SR is applied to recover the high-resolution image. Experimental results demonstrate that using our adaptive algorithm produces an improvement in SR performance with respect to non-adaptive training.

AB - The performance of dictionary-based super-resolution (SR) strongly depends on the contents of the training dataset. Nevertheless, many dictionary-based SR methods randomly select patches from of a larger set of training images to build their dictionaries [8, 14, 19, 20], thus relying on patches being diverse enough. This paper describes a dictionary building method for SR based on adaptively selecting an optimal subset of patches out of the training images. Each training image is divided into sub-image entities, named regions, of such a size that texture consistency is preserved and high-frequency (HF) energy is present. For each input patch to super-resolve, the best-fitting region is found through a Bayesian selection. In order to handle the high number of regions in the training dataset, a local Naive Bayes Nearest Neighbor (NBNN) approach is used. Trained with this adapted subset of patches, sparse coding SR is applied to recover the high-resolution image. Experimental results demonstrate that using our adaptive algorithm produces an improvement in SR performance with respect to non-adaptive training.

UR - http://www.scopus.com/inward/record.url?scp=84898450539&partnerID=8YFLogxK

U2 - 10.5244/C.27.37

DO - 10.5244/C.27.37

M3 - Paper

AN - SCOPUS:84898450539

T2 - 2013 24th British Machine Vision Conference, BMVC 2013

Y2 - 9 September 2013 through 13 September 2013

ER -

By the same author(s)