Efficient image enhancement using sparse source separation in the Retinex theory

Jongsu Yoon, Jangwon Choi, Yoonsik Choe

Research output: Contribution to journalArticle

Abstract

Color constancy is the feature of the human vision system (HVS) that ensures the relative constancy of the perceived color of objects under varying illumination conditions. The Retinex theory of machine vision systems is based on the HVS. Among Retinex algorithms, the physics-based algorithms are efficient; however, they generally do not satisfy the local characteristics of the original Retinex theory because they eliminate global illumination from their optimization. We apply the sparse source separation technique to the Retinex theory to present a physics-based algorithm that satisfies the locality characteristic of the original Retinex theory. Previous Retinex algorithms have limited use in image enhancement because the total variation Retinex results in an overly enhanced image and the sparse source separation Retinex cannot completely restore the original image. In contrast, our proposed method preserves the image edge and can very nearly replicate the original image without any special operation.

Original languageEnglish
Article number113103
JournalOptical Engineering
Volume56
Issue number11
DOIs
Publication statusPublished - 2017 Nov 1

Fingerprint

Source separation
image enhancement
Image enhancement
Physics
Lighting
illumination
Color
color
physics
computer vision
Computer vision
optimization

All Science Journal Classification (ASJC) codes

  • Atomic and Molecular Physics, and Optics
  • Engineering(all)

Cite this

@article{2855a0bd08374b8098034408ef02bab6,
title = "Efficient image enhancement using sparse source separation in the Retinex theory",
abstract = "Color constancy is the feature of the human vision system (HVS) that ensures the relative constancy of the perceived color of objects under varying illumination conditions. The Retinex theory of machine vision systems is based on the HVS. Among Retinex algorithms, the physics-based algorithms are efficient; however, they generally do not satisfy the local characteristics of the original Retinex theory because they eliminate global illumination from their optimization. We apply the sparse source separation technique to the Retinex theory to present a physics-based algorithm that satisfies the locality characteristic of the original Retinex theory. Previous Retinex algorithms have limited use in image enhancement because the total variation Retinex results in an overly enhanced image and the sparse source separation Retinex cannot completely restore the original image. In contrast, our proposed method preserves the image edge and can very nearly replicate the original image without any special operation.",
author = "Jongsu Yoon and Jangwon Choi and Yoonsik Choe",
year = "2017",
month = "11",
day = "1",
doi = "10.1117/1.OE.56.11.113103",
language = "English",
volume = "56",
journal = "Optical Engineering",
issn = "0091-3286",
publisher = "SPIE",
number = "11",

}

Efficient image enhancement using sparse source separation in the Retinex theory. / Yoon, Jongsu; Choi, Jangwon; Choe, Yoonsik.

In: Optical Engineering, Vol. 56, No. 11, 113103, 01.11.2017.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Efficient image enhancement using sparse source separation in the Retinex theory

AU - Yoon, Jongsu

AU - Choi, Jangwon

AU - Choe, Yoonsik

PY - 2017/11/1

Y1 - 2017/11/1

N2 - Color constancy is the feature of the human vision system (HVS) that ensures the relative constancy of the perceived color of objects under varying illumination conditions. The Retinex theory of machine vision systems is based on the HVS. Among Retinex algorithms, the physics-based algorithms are efficient; however, they generally do not satisfy the local characteristics of the original Retinex theory because they eliminate global illumination from their optimization. We apply the sparse source separation technique to the Retinex theory to present a physics-based algorithm that satisfies the locality characteristic of the original Retinex theory. Previous Retinex algorithms have limited use in image enhancement because the total variation Retinex results in an overly enhanced image and the sparse source separation Retinex cannot completely restore the original image. In contrast, our proposed method preserves the image edge and can very nearly replicate the original image without any special operation.

AB - Color constancy is the feature of the human vision system (HVS) that ensures the relative constancy of the perceived color of objects under varying illumination conditions. The Retinex theory of machine vision systems is based on the HVS. Among Retinex algorithms, the physics-based algorithms are efficient; however, they generally do not satisfy the local characteristics of the original Retinex theory because they eliminate global illumination from their optimization. We apply the sparse source separation technique to the Retinex theory to present a physics-based algorithm that satisfies the locality characteristic of the original Retinex theory. Previous Retinex algorithms have limited use in image enhancement because the total variation Retinex results in an overly enhanced image and the sparse source separation Retinex cannot completely restore the original image. In contrast, our proposed method preserves the image edge and can very nearly replicate the original image without any special operation.

UR - http://www.scopus.com/inward/record.url?scp=85034809893&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85034809893&partnerID=8YFLogxK

U2 - 10.1117/1.OE.56.11.113103

DO - 10.1117/1.OE.56.11.113103

M3 - Article

AN - SCOPUS:85034809893

VL - 56

JO - Optical Engineering

JF - Optical Engineering

SN - 0091-3286

IS - 11

M1 - 113103

ER -