Dark image enhancement based onpairwise target contrast and multi-scale detail boosting

Youngbae Kim, Yeong Jun Koh, Chulwoo Lee, Sehoon Kim, Chang-Su Kim

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

Abstract

A dark image enhancement algorithm based on the pairwise target contrast and the multi-scale detail boosting is proposed in this work. We first compute the pairwise target contrast between a pair of pixels, which represents the desired gray level difference of the two pixels in the output image. By aggregating the pairwise target contrasts for all pairs of pixels in an image, we formulate a cost function for the enhancement. By minimizing the cost function, we obtain the optimal transformation function and enhance the image. In addition, we propose a multi-scale approach to boost details in the globally enhanced image. Experimental results show that the proposed algorithm enhances the contrast and visibility of dark images more effectively than conventional algorithms.

Original languageEnglish
Title of host publicationProceedings - International Conference on Image Processing, ICIP
PublisherIEEE Computer Society
Pages1404-1408
Number of pages5
Volume2015-December
ISBN (Print)9781479983391
DOIs
Publication statusPublished - 2015 Dec 9
EventIEEE International Conference on Image Processing, ICIP 2015 - Quebec City, Canada
Duration: 2015 Sep 272015 Sep 30

Other

OtherIEEE International Conference on Image Processing, ICIP 2015
CountryCanada
CityQuebec City
Period15/9/2715/9/30

Fingerprint

Image enhancement
Pixels
Cost functions
Visibility

Keywords

  • backlit image enhancement
  • contrast enhancement
  • Dark image enhancement
  • multi-scale detail boosting
  • pairwise target contrast

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Kim, Y., Koh, Y. J., Lee, C., Kim, S., & Kim, C-S. (2015). Dark image enhancement based onpairwise target contrast and multi-scale detail boosting. In Proceedings - International Conference on Image Processing, ICIP (Vol. 2015-December, pp. 1404-1408). [7351031] IEEE Computer Society. https://doi.org/10.1109/ICIP.2015.7351031

Dark image enhancement based onpairwise target contrast and multi-scale detail boosting. / Kim, Youngbae; Koh, Yeong Jun; Lee, Chulwoo; Kim, Sehoon; Kim, Chang-Su.

Proceedings - International Conference on Image Processing, ICIP. Vol. 2015-December IEEE Computer Society, 2015. p. 1404-1408 7351031.

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

Kim, Y, Koh, YJ, Lee, C, Kim, S & Kim, C-S 2015, Dark image enhancement based onpairwise target contrast and multi-scale detail boosting. in Proceedings - International Conference on Image Processing, ICIP. vol. 2015-December, 7351031, IEEE Computer Society, pp. 1404-1408, IEEE International Conference on Image Processing, ICIP 2015, Quebec City, Canada, 15/9/27. https://doi.org/10.1109/ICIP.2015.7351031
Kim Y, Koh YJ, Lee C, Kim S, Kim C-S. Dark image enhancement based onpairwise target contrast and multi-scale detail boosting. In Proceedings - International Conference on Image Processing, ICIP. Vol. 2015-December. IEEE Computer Society. 2015. p. 1404-1408. 7351031 https://doi.org/10.1109/ICIP.2015.7351031
Kim, Youngbae ; Koh, Yeong Jun ; Lee, Chulwoo ; Kim, Sehoon ; Kim, Chang-Su. / Dark image enhancement based onpairwise target contrast and multi-scale detail boosting. Proceedings - International Conference on Image Processing, ICIP. Vol. 2015-December IEEE Computer Society, 2015. pp. 1404-1408
@inproceedings{790a4c6f46904657b0d45cf2d4f29ff2,
title = "Dark image enhancement based onpairwise target contrast and multi-scale detail boosting",
abstract = "A dark image enhancement algorithm based on the pairwise target contrast and the multi-scale detail boosting is proposed in this work. We first compute the pairwise target contrast between a pair of pixels, which represents the desired gray level difference of the two pixels in the output image. By aggregating the pairwise target contrasts for all pairs of pixels in an image, we formulate a cost function for the enhancement. By minimizing the cost function, we obtain the optimal transformation function and enhance the image. In addition, we propose a multi-scale approach to boost details in the globally enhanced image. Experimental results show that the proposed algorithm enhances the contrast and visibility of dark images more effectively than conventional algorithms.",
keywords = "backlit image enhancement, contrast enhancement, Dark image enhancement, multi-scale detail boosting, pairwise target contrast",
author = "Youngbae Kim and Koh, {Yeong Jun} and Chulwoo Lee and Sehoon Kim and Chang-Su Kim",
year = "2015",
month = "12",
day = "9",
doi = "10.1109/ICIP.2015.7351031",
language = "English",
isbn = "9781479983391",
volume = "2015-December",
pages = "1404--1408",
booktitle = "Proceedings - International Conference on Image Processing, ICIP",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Dark image enhancement based onpairwise target contrast and multi-scale detail boosting

AU - Kim, Youngbae

AU - Koh, Yeong Jun

AU - Lee, Chulwoo

AU - Kim, Sehoon

AU - Kim, Chang-Su

PY - 2015/12/9

Y1 - 2015/12/9

N2 - A dark image enhancement algorithm based on the pairwise target contrast and the multi-scale detail boosting is proposed in this work. We first compute the pairwise target contrast between a pair of pixels, which represents the desired gray level difference of the two pixels in the output image. By aggregating the pairwise target contrasts for all pairs of pixels in an image, we formulate a cost function for the enhancement. By minimizing the cost function, we obtain the optimal transformation function and enhance the image. In addition, we propose a multi-scale approach to boost details in the globally enhanced image. Experimental results show that the proposed algorithm enhances the contrast and visibility of dark images more effectively than conventional algorithms.

AB - A dark image enhancement algorithm based on the pairwise target contrast and the multi-scale detail boosting is proposed in this work. We first compute the pairwise target contrast between a pair of pixels, which represents the desired gray level difference of the two pixels in the output image. By aggregating the pairwise target contrasts for all pairs of pixels in an image, we formulate a cost function for the enhancement. By minimizing the cost function, we obtain the optimal transformation function and enhance the image. In addition, we propose a multi-scale approach to boost details in the globally enhanced image. Experimental results show that the proposed algorithm enhances the contrast and visibility of dark images more effectively than conventional algorithms.

KW - backlit image enhancement

KW - contrast enhancement

KW - Dark image enhancement

KW - multi-scale detail boosting

KW - pairwise target contrast

UR - http://www.scopus.com/inward/record.url?scp=84956603872&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84956603872&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2015.7351031

DO - 10.1109/ICIP.2015.7351031

M3 - Conference contribution

SN - 9781479983391

VL - 2015-December

SP - 1404

EP - 1408

BT - Proceedings - International Conference on Image Processing, ICIP

PB - IEEE Computer Society

ER -