Enhancement of noisy low-light images via structure-texture-noise decomposition

Jaemoon Lim, Minhyeok Heo, Chul Lee, Chang-Su Kim

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

2 Citations (Scopus)

Abstract

We propose a novel noisy low-light image enhancement algorithm via structure-texture-noise (STN) decomposition. We split an input image into structure, texture, and noise components, and enhance the structure and texture components separately. Specifically, we first enhance the contrast of the structure image, by extending a 2D histogram-based image enhancement scheme based on the characteristics of low-light images. Then, we reconstruct the texture image by retrieving texture components from the noise image, and enhance it by exploiting the perceptual response of the human visual system. Experimental results demonstrate that the proposed STN algorithm sharpens the texture and enhances the contrast more effectively than conventional algorithms, while removing noise without artifacts.

Original languageEnglish
Title of host publication2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9789881476821
DOIs
Publication statusPublished - 2017 Jan 17
Event2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2016 - Jeju, Korea, Republic of
Duration: 2016 Dec 132016 Dec 16

Other

Other2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2016
CountryKorea, Republic of
CityJeju
Period16/12/1316/12/16

Fingerprint

Textures
Decomposition
Image enhancement

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Information Systems
  • Signal Processing

Cite this

Lim, J., Heo, M., Lee, C., & Kim, C-S. (2017). Enhancement of noisy low-light images via structure-texture-noise decomposition. In 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2016 [7820710] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/APSIPA.2016.7820710

Enhancement of noisy low-light images via structure-texture-noise decomposition. / Lim, Jaemoon; Heo, Minhyeok; Lee, Chul; Kim, Chang-Su.

2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2016. Institute of Electrical and Electronics Engineers Inc., 2017. 7820710.

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

Lim, J, Heo, M, Lee, C & Kim, C-S 2017, Enhancement of noisy low-light images via structure-texture-noise decomposition. in 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2016., 7820710, Institute of Electrical and Electronics Engineers Inc., 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2016, Jeju, Korea, Republic of, 16/12/13. https://doi.org/10.1109/APSIPA.2016.7820710
Lim J, Heo M, Lee C, Kim C-S. Enhancement of noisy low-light images via structure-texture-noise decomposition. In 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2016. Institute of Electrical and Electronics Engineers Inc. 2017. 7820710 https://doi.org/10.1109/APSIPA.2016.7820710
Lim, Jaemoon ; Heo, Minhyeok ; Lee, Chul ; Kim, Chang-Su. / Enhancement of noisy low-light images via structure-texture-noise decomposition. 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2016. Institute of Electrical and Electronics Engineers Inc., 2017.
@inproceedings{7dda6e8e570842e18932bb71a9bee68c,
title = "Enhancement of noisy low-light images via structure-texture-noise decomposition",
abstract = "We propose a novel noisy low-light image enhancement algorithm via structure-texture-noise (STN) decomposition. We split an input image into structure, texture, and noise components, and enhance the structure and texture components separately. Specifically, we first enhance the contrast of the structure image, by extending a 2D histogram-based image enhancement scheme based on the characteristics of low-light images. Then, we reconstruct the texture image by retrieving texture components from the noise image, and enhance it by exploiting the perceptual response of the human visual system. Experimental results demonstrate that the proposed STN algorithm sharpens the texture and enhances the contrast more effectively than conventional algorithms, while removing noise without artifacts.",
author = "Jaemoon Lim and Minhyeok Heo and Chul Lee and Chang-Su Kim",
year = "2017",
month = "1",
day = "17",
doi = "10.1109/APSIPA.2016.7820710",
language = "English",
booktitle = "2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Enhancement of noisy low-light images via structure-texture-noise decomposition

AU - Lim, Jaemoon

AU - Heo, Minhyeok

AU - Lee, Chul

AU - Kim, Chang-Su

PY - 2017/1/17

Y1 - 2017/1/17

N2 - We propose a novel noisy low-light image enhancement algorithm via structure-texture-noise (STN) decomposition. We split an input image into structure, texture, and noise components, and enhance the structure and texture components separately. Specifically, we first enhance the contrast of the structure image, by extending a 2D histogram-based image enhancement scheme based on the characteristics of low-light images. Then, we reconstruct the texture image by retrieving texture components from the noise image, and enhance it by exploiting the perceptual response of the human visual system. Experimental results demonstrate that the proposed STN algorithm sharpens the texture and enhances the contrast more effectively than conventional algorithms, while removing noise without artifacts.

AB - We propose a novel noisy low-light image enhancement algorithm via structure-texture-noise (STN) decomposition. We split an input image into structure, texture, and noise components, and enhance the structure and texture components separately. Specifically, we first enhance the contrast of the structure image, by extending a 2D histogram-based image enhancement scheme based on the characteristics of low-light images. Then, we reconstruct the texture image by retrieving texture components from the noise image, and enhance it by exploiting the perceptual response of the human visual system. Experimental results demonstrate that the proposed STN algorithm sharpens the texture and enhances the contrast more effectively than conventional algorithms, while removing noise without artifacts.

UR - http://www.scopus.com/inward/record.url?scp=85013805603&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85013805603&partnerID=8YFLogxK

U2 - 10.1109/APSIPA.2016.7820710

DO - 10.1109/APSIPA.2016.7820710

M3 - Conference contribution

AN - SCOPUS:85013805603

BT - 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -