Self-similarity based image super-resolution on frequency domain

Sae Jin Park; Oh Young Lee; Jong Ok Kim

doi:10.1109/APSIPA.2013.6694232

Self-similarity based image super-resolution on frequency domain

Sae Jin Park
, Oh Young Lee
, Jong Ok Kim

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

11 Citations (Scopus)

Abstract

Self-similarity has been popularly exploited for image super resolution in recent years. Image is decomposed into LF (low frequency) and HF (high frequency) components, and similar patches are searched in the LF domain across the pyramid scales of the original image. Once a similar LF patch is found, the LF is combined with the corresponding HR patch, and we reconstruct the HR (high resolution) version. In this paper, we separately search similar LR and HR patches in the LF and HF domains, respectively. In addition, self-similarity based SR is applied to the new structure-texture domain instead of the existing LF and HF. Experimental results show that the proposed method outperforms several conventional SR algorithms based on self-similarity.

Original language	English
Title of host publication	2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013
DOIs	https://doi.org/10.1109/APSIPA.2013.6694232
Publication status	Published - 2013
Event	2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013 - Kaohsiung, Taiwan, Province of China Duration: 2013 Oct 29 → 2013 Nov 1

Publication series

Name	2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013

Other

Other	2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013
Country/Territory	Taiwan, Province of China
City	Kaohsiung
Period	13/10/29 → 13/11/1

ASJC Scopus subject areas

Information Systems
Signal Processing

Access to Document

10.1109/APSIPA.2013.6694232

Cite this

Park, S. J., Lee, O. Y., & Kim, J. O. (2013). Self-similarity based image super-resolution on frequency domain. In 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013 Article 6694232 (2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013). https://doi.org/10.1109/APSIPA.2013.6694232

Self-similarity based image super-resolution on frequency domain. / Park, Sae Jin; Lee, Oh Young; Kim, Jong Ok.
2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013. 2013. 6694232 (2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Park, SJ, Lee, OY & Kim, JO 2013, Self-similarity based image super-resolution on frequency domain. in 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013., 6694232, 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013, 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013, Kaohsiung, Taiwan, Province of China, 13/10/29. https://doi.org/10.1109/APSIPA.2013.6694232

@inproceedings{b5ea9be9534544cdaba22ef11c0b4153,

title = "Self-similarity based image super-resolution on frequency domain",

abstract = "Self-similarity has been popularly exploited for image super resolution in recent years. Image is decomposed into LF (low frequency) and HF (high frequency) components, and similar patches are searched in the LF domain across the pyramid scales of the original image. Once a similar LF patch is found, the LF is combined with the corresponding HR patch, and we reconstruct the HR (high resolution) version. In this paper, we separately search similar LR and HR patches in the LF and HF domains, respectively. In addition, self-similarity based SR is applied to the new structure-texture domain instead of the existing LF and HF. Experimental results show that the proposed method outperforms several conventional SR algorithms based on self-similarity.",

author = "Park, \{Sae Jin\} and Lee, \{Oh Young\} and Kim, \{Jong Ok\}",

year = "2013",

doi = "10.1109/APSIPA.2013.6694232",

language = "English",

isbn = "9789869000604",

series = "2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013",

booktitle = "2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013",

note = "2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013 ; Conference date: 29-10-2013 Through 01-11-2013",

}

TY - GEN

T1 - Self-similarity based image super-resolution on frequency domain

AU - Park, Sae Jin

AU - Lee, Oh Young

AU - Kim, Jong Ok

PY - 2013

Y1 - 2013

N2 - Self-similarity has been popularly exploited for image super resolution in recent years. Image is decomposed into LF (low frequency) and HF (high frequency) components, and similar patches are searched in the LF domain across the pyramid scales of the original image. Once a similar LF patch is found, the LF is combined with the corresponding HR patch, and we reconstruct the HR (high resolution) version. In this paper, we separately search similar LR and HR patches in the LF and HF domains, respectively. In addition, self-similarity based SR is applied to the new structure-texture domain instead of the existing LF and HF. Experimental results show that the proposed method outperforms several conventional SR algorithms based on self-similarity.

AB - Self-similarity has been popularly exploited for image super resolution in recent years. Image is decomposed into LF (low frequency) and HF (high frequency) components, and similar patches are searched in the LF domain across the pyramid scales of the original image. Once a similar LF patch is found, the LF is combined with the corresponding HR patch, and we reconstruct the HR (high resolution) version. In this paper, we separately search similar LR and HR patches in the LF and HF domains, respectively. In addition, self-similarity based SR is applied to the new structure-texture domain instead of the existing LF and HF. Experimental results show that the proposed method outperforms several conventional SR algorithms based on self-similarity.

UR - https://www.scopus.com/pages/publications/84893339402

UR - https://www.scopus.com/pages/publications/84893339402#tab=citedBy

U2 - 10.1109/APSIPA.2013.6694232

DO - 10.1109/APSIPA.2013.6694232

M3 - Conference contribution

AN - SCOPUS:84893339402

SN - 9789869000604

T3 - 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013

BT - 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013

T2 - 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013

Y2 - 29 October 2013 through 1 November 2013

ER -

Self-similarity based image super-resolution on frequency domain

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this