Adaptive self-similarity based image super-resolution using non local means

Ji Hoon Choi, Sae Jin Park, Dae Yeol Lee, Sung Chang Lim, Jin Soo Choi, Jong-Ok Kim

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

1 Citation (Scopus)

Abstract

Self-similarity based SR method on the LF-HF domain basically relies on the assumption that LF patch is highly correlated with HF patch. However, this assumption is content-specific significantly, and we can occasionally observe little correlation between LF and HF patch especially for texture region of natural images. In this paper we propose a new self-similarity based SR method to reflect this observation. There are two differences between the proposed and existing methods. First, HF details of target HR image are recovered by finding the similar patches on the MF domain in case of texture region. Second, the proposed method performs pixel-based reconstruction by adopting the concept of non-local means. Experimental results show that the proposed method can reconstruct more realistic image details.

Original languageEnglish
Title of host publication2014 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Print)9786163618238
DOIs
Publication statusPublished - 2014 Feb 12
Event2014 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2014 - Chiang Mai, Thailand
Duration: 2014 Dec 92014 Dec 12

Other

Other2014 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2014
CountryThailand
CityChiang Mai
Period14/12/914/12/12

Fingerprint

Textures
Pixels

ASJC Scopus subject areas

  • Signal Processing
  • Information Systems

Cite this

Choi, J. H., Park, S. J., Lee, D. Y., Lim, S. C., Choi, J. S., & Kim, J-O. (2014). Adaptive self-similarity based image super-resolution using non local means. In 2014 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2014 [7041605] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/APSIPA.2014.7041605

Adaptive self-similarity based image super-resolution using non local means. / Choi, Ji Hoon; Park, Sae Jin; Lee, Dae Yeol; Lim, Sung Chang; Choi, Jin Soo; Kim, Jong-Ok.

2014 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2014. Institute of Electrical and Electronics Engineers Inc., 2014. 7041605.

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

Choi, JH, Park, SJ, Lee, DY, Lim, SC, Choi, JS & Kim, J-O 2014, Adaptive self-similarity based image super-resolution using non local means. in 2014 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2014., 7041605, Institute of Electrical and Electronics Engineers Inc., 2014 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2014, Chiang Mai, Thailand, 14/12/9. https://doi.org/10.1109/APSIPA.2014.7041605
Choi JH, Park SJ, Lee DY, Lim SC, Choi JS, Kim J-O. Adaptive self-similarity based image super-resolution using non local means. In 2014 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2014. Institute of Electrical and Electronics Engineers Inc. 2014. 7041605 https://doi.org/10.1109/APSIPA.2014.7041605
Choi, Ji Hoon ; Park, Sae Jin ; Lee, Dae Yeol ; Lim, Sung Chang ; Choi, Jin Soo ; Kim, Jong-Ok. / Adaptive self-similarity based image super-resolution using non local means. 2014 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2014. Institute of Electrical and Electronics Engineers Inc., 2014.
@inproceedings{080411180089400abf3abeebf6a0ca4f,
title = "Adaptive self-similarity based image super-resolution using non local means",
abstract = "Self-similarity based SR method on the LF-HF domain basically relies on the assumption that LF patch is highly correlated with HF patch. However, this assumption is content-specific significantly, and we can occasionally observe little correlation between LF and HF patch especially for texture region of natural images. In this paper we propose a new self-similarity based SR method to reflect this observation. There are two differences between the proposed and existing methods. First, HF details of target HR image are recovered by finding the similar patches on the MF domain in case of texture region. Second, the proposed method performs pixel-based reconstruction by adopting the concept of non-local means. Experimental results show that the proposed method can reconstruct more realistic image details.",
author = "Choi, {Ji Hoon} and Park, {Sae Jin} and Lee, {Dae Yeol} and Lim, {Sung Chang} and Choi, {Jin Soo} and Jong-Ok Kim",
year = "2014",
month = "2",
day = "12",
doi = "10.1109/APSIPA.2014.7041605",
language = "English",
isbn = "9786163618238",
booktitle = "2014 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Adaptive self-similarity based image super-resolution using non local means

AU - Choi, Ji Hoon

AU - Park, Sae Jin

AU - Lee, Dae Yeol

AU - Lim, Sung Chang

AU - Choi, Jin Soo

AU - Kim, Jong-Ok

PY - 2014/2/12

Y1 - 2014/2/12

N2 - Self-similarity based SR method on the LF-HF domain basically relies on the assumption that LF patch is highly correlated with HF patch. However, this assumption is content-specific significantly, and we can occasionally observe little correlation between LF and HF patch especially for texture region of natural images. In this paper we propose a new self-similarity based SR method to reflect this observation. There are two differences between the proposed and existing methods. First, HF details of target HR image are recovered by finding the similar patches on the MF domain in case of texture region. Second, the proposed method performs pixel-based reconstruction by adopting the concept of non-local means. Experimental results show that the proposed method can reconstruct more realistic image details.

AB - Self-similarity based SR method on the LF-HF domain basically relies on the assumption that LF patch is highly correlated with HF patch. However, this assumption is content-specific significantly, and we can occasionally observe little correlation between LF and HF patch especially for texture region of natural images. In this paper we propose a new self-similarity based SR method to reflect this observation. There are two differences between the proposed and existing methods. First, HF details of target HR image are recovered by finding the similar patches on the MF domain in case of texture region. Second, the proposed method performs pixel-based reconstruction by adopting the concept of non-local means. Experimental results show that the proposed method can reconstruct more realistic image details.

UR - http://www.scopus.com/inward/record.url?scp=84949924858&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84949924858&partnerID=8YFLogxK

U2 - 10.1109/APSIPA.2014.7041605

DO - 10.1109/APSIPA.2014.7041605

M3 - Conference contribution

AN - SCOPUS:84949924858

SN - 9786163618238

BT - 2014 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -