Underwater image enhancement through depth estimation based on random forest

Shen Chuan Tai, Ting Chou Tsai, Jyun Han Huang

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Light absorption and scattering in underwater environments can result in low-contrast images with a distinct color cast. This paper proposes a systematic framework for the enhancement of underwater images. Light transmission is estimated using the random forest algorithm. RGB values, luminance, color difference, blurriness, and the dark channel are treated as features in training and estimation. Transmission is calculated using an ensemble machine learning algorithm to deal with a variety of conditions encountered in underwater environments. A color compensation and contrast enhancement algorithm based on depth information was also developed with the aim of improving the visual quality of underwater images. Experimental results demonstrate that the proposed scheme outperforms existing methods with regard to subjective visual quality as well as objective measurements.

Original languageEnglish
Article number063026
JournalJournal of Electronic Imaging
Volume26
Issue number6
DOIs
Publication statusPublished - 2017 Nov 1

Fingerprint

image enhancement
Image enhancement
Color
color
machine learning
augmentation
light transmission
image contrast
Light transmission
electromagnetic absorption
luminance
Light scattering
Light absorption
Learning algorithms
Learning systems
casts
Luminance
education
light scattering

All Science Journal Classification (ASJC) codes

  • Atomic and Molecular Physics, and Optics
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

@article{5ed514fd97874b64b40dd20680a6946f,
title = "Underwater image enhancement through depth estimation based on random forest",
abstract = "Light absorption and scattering in underwater environments can result in low-contrast images with a distinct color cast. This paper proposes a systematic framework for the enhancement of underwater images. Light transmission is estimated using the random forest algorithm. RGB values, luminance, color difference, blurriness, and the dark channel are treated as features in training and estimation. Transmission is calculated using an ensemble machine learning algorithm to deal with a variety of conditions encountered in underwater environments. A color compensation and contrast enhancement algorithm based on depth information was also developed with the aim of improving the visual quality of underwater images. Experimental results demonstrate that the proposed scheme outperforms existing methods with regard to subjective visual quality as well as objective measurements.",
author = "Tai, {Shen Chuan} and Tsai, {Ting Chou} and Huang, {Jyun Han}",
year = "2017",
month = "11",
day = "1",
doi = "10.1117/1.JEI.26.6.063026",
language = "English",
volume = "26",
journal = "Journal of Electronic Imaging",
issn = "1017-9909",
publisher = "SPIE",
number = "6",

}

Underwater image enhancement through depth estimation based on random forest. / Tai, Shen Chuan; Tsai, Ting Chou; Huang, Jyun Han.

In: Journal of Electronic Imaging, Vol. 26, No. 6, 063026, 01.11.2017.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Underwater image enhancement through depth estimation based on random forest

AU - Tai, Shen Chuan

AU - Tsai, Ting Chou

AU - Huang, Jyun Han

PY - 2017/11/1

Y1 - 2017/11/1

N2 - Light absorption and scattering in underwater environments can result in low-contrast images with a distinct color cast. This paper proposes a systematic framework for the enhancement of underwater images. Light transmission is estimated using the random forest algorithm. RGB values, luminance, color difference, blurriness, and the dark channel are treated as features in training and estimation. Transmission is calculated using an ensemble machine learning algorithm to deal with a variety of conditions encountered in underwater environments. A color compensation and contrast enhancement algorithm based on depth information was also developed with the aim of improving the visual quality of underwater images. Experimental results demonstrate that the proposed scheme outperforms existing methods with regard to subjective visual quality as well as objective measurements.

AB - Light absorption and scattering in underwater environments can result in low-contrast images with a distinct color cast. This paper proposes a systematic framework for the enhancement of underwater images. Light transmission is estimated using the random forest algorithm. RGB values, luminance, color difference, blurriness, and the dark channel are treated as features in training and estimation. Transmission is calculated using an ensemble machine learning algorithm to deal with a variety of conditions encountered in underwater environments. A color compensation and contrast enhancement algorithm based on depth information was also developed with the aim of improving the visual quality of underwater images. Experimental results demonstrate that the proposed scheme outperforms existing methods with regard to subjective visual quality as well as objective measurements.

UR - http://www.scopus.com/inward/record.url?scp=85042436753&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042436753&partnerID=8YFLogxK

U2 - 10.1117/1.JEI.26.6.063026

DO - 10.1117/1.JEI.26.6.063026

M3 - Article

AN - SCOPUS:85042436753

VL - 26

JO - Journal of Electronic Imaging

JF - Journal of Electronic Imaging

SN - 1017-9909

IS - 6

M1 - 063026

ER -