Details
Original language | English |
---|---|
Publication status | Published - 2013 |
Event | 2013 24th British Machine Vision Conference, BMVC 2013 - Bristol, United Kingdom (UK) Duration: 9 Sept 2013 → 13 Sept 2013 |
Conference
Conference | 2013 24th British Machine Vision Conference, BMVC 2013 |
---|---|
Country/Territory | United Kingdom (UK) |
City | Bristol |
Period | 9 Sept 2013 → 13 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
- Computer Science(all)
- Computer Vision and Pattern Recognition
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
2013. Paper presented at 2013 24th British Machine Vision Conference, BMVC 2013, Bristol, United Kingdom (UK).
Research output: Contribution to conference › Paper › Research › peer review
}
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 -