High frequency super-resolution for image enhancement

Oh Young Lee, Sae Jin Park, Jae Woo Kim, Jong-Ok Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Bayesian based MF-SR (multi-frame superresolution) has been used as a popular and effective SR model. However, texture region is not reconstructed sufficiently because it works on the spatial domain. In this paper, we extend the MF-SR method to operate on the frequency domain for the improvement of HF information as much as possible. For this, we propose a spatially weighted bilateral total variation model as a regularization term for Bayesian estimation. Experimental results show that the proposed method can recover texture region with reduced noise, compared to conventional methods.

Original languageEnglish
Title of host publicationProceedings of the International Symposium on Consumer Electronics, ISCE
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Print)9781479945924
DOIs
Publication statusPublished - 2014 Jan 1
Event18th IEEE International Symposium on Consumer Electronics, ISCE 2014 - Jeju, Korea, Republic of
Duration: 2014 Jun 222014 Jun 25

Other

Other18th IEEE International Symposium on Consumer Electronics, ISCE 2014
CountryKorea, Republic of
CityJeju
Period14/6/2214/6/25

Fingerprint

Image enhancement
Textures

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Lee, O. Y., Park, S. J., Kim, J. W., & Kim, J-O. (2014). High frequency super-resolution for image enhancement. In Proceedings of the International Symposium on Consumer Electronics, ISCE [6884422] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISCE.2014.6884422

High frequency super-resolution for image enhancement. / Lee, Oh Young; Park, Sae Jin; Kim, Jae Woo; Kim, Jong-Ok.

Proceedings of the International Symposium on Consumer Electronics, ISCE. Institute of Electrical and Electronics Engineers Inc., 2014. 6884422.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lee, OY, Park, SJ, Kim, JW & Kim, J-O 2014, High frequency super-resolution for image enhancement. in Proceedings of the International Symposium on Consumer Electronics, ISCE., 6884422, Institute of Electrical and Electronics Engineers Inc., 18th IEEE International Symposium on Consumer Electronics, ISCE 2014, Jeju, Korea, Republic of, 14/6/22. https://doi.org/10.1109/ISCE.2014.6884422
Lee OY, Park SJ, Kim JW, Kim J-O. High frequency super-resolution for image enhancement. In Proceedings of the International Symposium on Consumer Electronics, ISCE. Institute of Electrical and Electronics Engineers Inc. 2014. 6884422 https://doi.org/10.1109/ISCE.2014.6884422
Lee, Oh Young ; Park, Sae Jin ; Kim, Jae Woo ; Kim, Jong-Ok. / High frequency super-resolution for image enhancement. Proceedings of the International Symposium on Consumer Electronics, ISCE. Institute of Electrical and Electronics Engineers Inc., 2014.
@inproceedings{d733d533e2de43d7b80300af0eb3a3b2,
title = "High frequency super-resolution for image enhancement",
abstract = "Bayesian based MF-SR (multi-frame superresolution) has been used as a popular and effective SR model. However, texture region is not reconstructed sufficiently because it works on the spatial domain. In this paper, we extend the MF-SR method to operate on the frequency domain for the improvement of HF information as much as possible. For this, we propose a spatially weighted bilateral total variation model as a regularization term for Bayesian estimation. Experimental results show that the proposed method can recover texture region with reduced noise, compared to conventional methods.",
keywords = "high frequency SR, image enhancement, multi-frame SR, spatially weighted bilateral total variance",
author = "Lee, {Oh Young} and Park, {Sae Jin} and Kim, {Jae Woo} and Jong-Ok Kim",
year = "2014",
month = "1",
day = "1",
doi = "10.1109/ISCE.2014.6884422",
language = "English",
isbn = "9781479945924",
booktitle = "Proceedings of the International Symposium on Consumer Electronics, ISCE",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - High frequency super-resolution for image enhancement

AU - Lee, Oh Young

AU - Park, Sae Jin

AU - Kim, Jae Woo

AU - Kim, Jong-Ok

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Bayesian based MF-SR (multi-frame superresolution) has been used as a popular and effective SR model. However, texture region is not reconstructed sufficiently because it works on the spatial domain. In this paper, we extend the MF-SR method to operate on the frequency domain for the improvement of HF information as much as possible. For this, we propose a spatially weighted bilateral total variation model as a regularization term for Bayesian estimation. Experimental results show that the proposed method can recover texture region with reduced noise, compared to conventional methods.

AB - Bayesian based MF-SR (multi-frame superresolution) has been used as a popular and effective SR model. However, texture region is not reconstructed sufficiently because it works on the spatial domain. In this paper, we extend the MF-SR method to operate on the frequency domain for the improvement of HF information as much as possible. For this, we propose a spatially weighted bilateral total variation model as a regularization term for Bayesian estimation. Experimental results show that the proposed method can recover texture region with reduced noise, compared to conventional methods.

KW - high frequency SR

KW - image enhancement

KW - multi-frame SR

KW - spatially weighted bilateral total variance

UR - http://www.scopus.com/inward/record.url?scp=84907417875&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84907417875&partnerID=8YFLogxK

U2 - 10.1109/ISCE.2014.6884422

DO - 10.1109/ISCE.2014.6884422

M3 - Conference contribution

AN - SCOPUS:84907417875

SN - 9781479945924

BT - Proceedings of the International Symposium on Consumer Electronics, ISCE

PB - Institute of Electrical and Electronics Engineers Inc.

ER -