Iterative image dehazing using the dark channel prior

Sung Ho Lee, Seung Won Jung, Sung-Jea Ko

Research output: Contribution to journalArticle

Abstract

The dark channel prior (DCP)-based image dehazing method has been widely used for enhancing visibility of outdoor images. However, since the DCP-based method assumes that the minimum values within local patches of natural outdoor haze-free images are zero, underestimation of the transmission is inevitable when the assumption does not hold. In this letter, a novel iterative image dehazing algorithm is proposed to compensate for the underestimated transmission. Experimental results show that the proposed method can improve the dehazing performance by increasing the transmission estimation accuracy.

Original languageEnglish
Pages (from-to)1904-1906
Number of pages3
JournalIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
VolumeE99A
Issue number10
DOIs
Publication statusPublished - 2016 Oct 1

Fingerprint

Visibility
Patch
Zero
Experimental Results

Keywords

  • Dark channel prior
  • Haze removal
  • Iterative transmission estimation
  • Single image dehazing

ASJC Scopus subject areas

  • Signal Processing
  • Computer Graphics and Computer-Aided Design
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Iterative image dehazing using the dark channel prior. / Lee, Sung Ho; Jung, Seung Won; Ko, Sung-Jea.

In: IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, Vol. E99A, No. 10, 01.10.2016, p. 1904-1906.

Research output: Contribution to journalArticle

@article{7db658fe610c43218cee26ad5ba47483,
title = "Iterative image dehazing using the dark channel prior",
abstract = "The dark channel prior (DCP)-based image dehazing method has been widely used for enhancing visibility of outdoor images. However, since the DCP-based method assumes that the minimum values within local patches of natural outdoor haze-free images are zero, underestimation of the transmission is inevitable when the assumption does not hold. In this letter, a novel iterative image dehazing algorithm is proposed to compensate for the underestimated transmission. Experimental results show that the proposed method can improve the dehazing performance by increasing the transmission estimation accuracy.",
keywords = "Dark channel prior, Haze removal, Iterative transmission estimation, Single image dehazing",
author = "Lee, {Sung Ho} and Jung, {Seung Won} and Sung-Jea Ko",
year = "2016",
month = "10",
day = "1",
doi = "10.1587/transfun.E99.A.1904",
language = "English",
volume = "E99A",
pages = "1904--1906",
journal = "IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences",
issn = "0916-8508",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "10",

}

TY - JOUR

T1 - Iterative image dehazing using the dark channel prior

AU - Lee, Sung Ho

AU - Jung, Seung Won

AU - Ko, Sung-Jea

PY - 2016/10/1

Y1 - 2016/10/1

N2 - The dark channel prior (DCP)-based image dehazing method has been widely used for enhancing visibility of outdoor images. However, since the DCP-based method assumes that the minimum values within local patches of natural outdoor haze-free images are zero, underestimation of the transmission is inevitable when the assumption does not hold. In this letter, a novel iterative image dehazing algorithm is proposed to compensate for the underestimated transmission. Experimental results show that the proposed method can improve the dehazing performance by increasing the transmission estimation accuracy.

AB - The dark channel prior (DCP)-based image dehazing method has been widely used for enhancing visibility of outdoor images. However, since the DCP-based method assumes that the minimum values within local patches of natural outdoor haze-free images are zero, underestimation of the transmission is inevitable when the assumption does not hold. In this letter, a novel iterative image dehazing algorithm is proposed to compensate for the underestimated transmission. Experimental results show that the proposed method can improve the dehazing performance by increasing the transmission estimation accuracy.

KW - Dark channel prior

KW - Haze removal

KW - Iterative transmission estimation

KW - Single image dehazing

UR - http://www.scopus.com/inward/record.url?scp=84989322073&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84989322073&partnerID=8YFLogxK

U2 - 10.1587/transfun.E99.A.1904

DO - 10.1587/transfun.E99.A.1904

M3 - Article

AN - SCOPUS:84989322073

VL - E99A

SP - 1904

EP - 1906

JO - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

JF - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

SN - 0916-8508

IS - 10

ER -