Luminosity and contrast normalization in color retinal images based on standard reference image

Ehsan S. Varnousfaderani, Siamak Yousefi, Akram Belghith, Michael H. Goldbaum

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

3 Citations (Scopus)

Abstract

Color retinal images are used manually or automatically for diagnosis and monitoring progression of a retinal diseases. Color retinal images have large luminosity and contrast variability within and across images due to the large natural variations in retinal pigmentation and complex imaging setups. The quality of retinal images may affect the performance of automatic screening tools therefore different normalization methods are developed to uniform data before applying any further analysis or processing. In this paper we propose a new reliable method to remove non-uniform illumination in retinal images and improve their contrast based on contrast of the reference image. The non-uniform illumination is removed by normalizing luminance image using local mean and standard deviation. Then the contrast is enhanced by shifting histograms of uniform illuminated retinal image toward histograms of the reference image to have similar histogram peaks. This process improve the contrast without changing inter correlation of pixels in different color channels. In compliance with the way humans perceive color, the uniform color space of LUV is used for normalization. The proposed method is widely tested on large dataset of retinal images with present of different pathologies such as Exudate, Lesion, Hemorrhages and Cotton-Wool and in different illumination conditions and imaging setups. Results shows that proposed method successfully equalize illumination and enhances contrast of retinal images without adding any extra artifacts.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2016
Subtitle of host publicationImage Processing
EditorsMartin A. Styner, Elsa D. Angelini, Elsa D. Angelini
PublisherSPIE
Volume9784
ISBN (Electronic)9781510600195
DOIs
StatePublished - Jan 1 2016
Externally publishedYes
EventMedical Imaging 2016: Image Processing - San Diego, United States
Duration: Mar 1 2016Mar 3 2016

Other

OtherMedical Imaging 2016: Image Processing
CountryUnited States
CitySan Diego
Period3/1/163/3/16

Fingerprint

retinal images
Luminance
Lighting
Color
luminosity
color
illumination
histograms
Imaging techniques
Retinal Diseases
Wool
Pigmentation
Pathology
Exudates and Transudates
Artifacts
hemorrhages
Cotton
wool
normalizing
Screening

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Varnousfaderani, E. S., Yousefi, S., Belghith, A., & Goldbaum, M. H. (2016). Luminosity and contrast normalization in color retinal images based on standard reference image. In M. A. Styner, E. D. Angelini, & E. D. Angelini (Eds.), Medical Imaging 2016: Image Processing (Vol. 9784). [97843N] SPIE. https://doi.org/10.1117/12.2217131

Luminosity and contrast normalization in color retinal images based on standard reference image. / Varnousfaderani, Ehsan S.; Yousefi, Siamak; Belghith, Akram; Goldbaum, Michael H.

Medical Imaging 2016: Image Processing. ed. / Martin A. Styner; Elsa D. Angelini; Elsa D. Angelini. Vol. 9784 SPIE, 2016. 97843N.

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

Varnousfaderani, ES, Yousefi, S, Belghith, A & Goldbaum, MH 2016, Luminosity and contrast normalization in color retinal images based on standard reference image. in MA Styner, ED Angelini & ED Angelini (eds), Medical Imaging 2016: Image Processing. vol. 9784, 97843N, SPIE, Medical Imaging 2016: Image Processing, San Diego, United States, 3/1/16. https://doi.org/10.1117/12.2217131
Varnousfaderani ES, Yousefi S, Belghith A, Goldbaum MH. Luminosity and contrast normalization in color retinal images based on standard reference image. In Styner MA, Angelini ED, Angelini ED, editors, Medical Imaging 2016: Image Processing. Vol. 9784. SPIE. 2016. 97843N https://doi.org/10.1117/12.2217131
Varnousfaderani, Ehsan S. ; Yousefi, Siamak ; Belghith, Akram ; Goldbaum, Michael H. / Luminosity and contrast normalization in color retinal images based on standard reference image. Medical Imaging 2016: Image Processing. editor / Martin A. Styner ; Elsa D. Angelini ; Elsa D. Angelini. Vol. 9784 SPIE, 2016.
@inproceedings{ff1a657ad5bf4cb4b30d68bd9336624e,
title = "Luminosity and contrast normalization in color retinal images based on standard reference image",
abstract = "Color retinal images are used manually or automatically for diagnosis and monitoring progression of a retinal diseases. Color retinal images have large luminosity and contrast variability within and across images due to the large natural variations in retinal pigmentation and complex imaging setups. The quality of retinal images may affect the performance of automatic screening tools therefore different normalization methods are developed to uniform data before applying any further analysis or processing. In this paper we propose a new reliable method to remove non-uniform illumination in retinal images and improve their contrast based on contrast of the reference image. The non-uniform illumination is removed by normalizing luminance image using local mean and standard deviation. Then the contrast is enhanced by shifting histograms of uniform illuminated retinal image toward histograms of the reference image to have similar histogram peaks. This process improve the contrast without changing inter correlation of pixels in different color channels. In compliance with the way humans perceive color, the uniform color space of LUV is used for normalization. The proposed method is widely tested on large dataset of retinal images with present of different pathologies such as Exudate, Lesion, Hemorrhages and Cotton-Wool and in different illumination conditions and imaging setups. Results shows that proposed method successfully equalize illumination and enhances contrast of retinal images without adding any extra artifacts.",
author = "Varnousfaderani, {Ehsan S.} and Siamak Yousefi and Akram Belghith and Goldbaum, {Michael H.}",
year = "2016",
month = "1",
day = "1",
doi = "10.1117/12.2217131",
language = "English (US)",
volume = "9784",
editor = "Styner, {Martin A.} and Angelini, {Elsa D.} and Angelini, {Elsa D.}",
booktitle = "Medical Imaging 2016",
publisher = "SPIE",
address = "United States",

}

TY - GEN

T1 - Luminosity and contrast normalization in color retinal images based on standard reference image

AU - Varnousfaderani, Ehsan S.

AU - Yousefi, Siamak

AU - Belghith, Akram

AU - Goldbaum, Michael H.

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Color retinal images are used manually or automatically for diagnosis and monitoring progression of a retinal diseases. Color retinal images have large luminosity and contrast variability within and across images due to the large natural variations in retinal pigmentation and complex imaging setups. The quality of retinal images may affect the performance of automatic screening tools therefore different normalization methods are developed to uniform data before applying any further analysis or processing. In this paper we propose a new reliable method to remove non-uniform illumination in retinal images and improve their contrast based on contrast of the reference image. The non-uniform illumination is removed by normalizing luminance image using local mean and standard deviation. Then the contrast is enhanced by shifting histograms of uniform illuminated retinal image toward histograms of the reference image to have similar histogram peaks. This process improve the contrast without changing inter correlation of pixels in different color channels. In compliance with the way humans perceive color, the uniform color space of LUV is used for normalization. The proposed method is widely tested on large dataset of retinal images with present of different pathologies such as Exudate, Lesion, Hemorrhages and Cotton-Wool and in different illumination conditions and imaging setups. Results shows that proposed method successfully equalize illumination and enhances contrast of retinal images without adding any extra artifacts.

AB - Color retinal images are used manually or automatically for diagnosis and monitoring progression of a retinal diseases. Color retinal images have large luminosity and contrast variability within and across images due to the large natural variations in retinal pigmentation and complex imaging setups. The quality of retinal images may affect the performance of automatic screening tools therefore different normalization methods are developed to uniform data before applying any further analysis or processing. In this paper we propose a new reliable method to remove non-uniform illumination in retinal images and improve their contrast based on contrast of the reference image. The non-uniform illumination is removed by normalizing luminance image using local mean and standard deviation. Then the contrast is enhanced by shifting histograms of uniform illuminated retinal image toward histograms of the reference image to have similar histogram peaks. This process improve the contrast without changing inter correlation of pixels in different color channels. In compliance with the way humans perceive color, the uniform color space of LUV is used for normalization. The proposed method is widely tested on large dataset of retinal images with present of different pathologies such as Exudate, Lesion, Hemorrhages and Cotton-Wool and in different illumination conditions and imaging setups. Results shows that proposed method successfully equalize illumination and enhances contrast of retinal images without adding any extra artifacts.

UR - http://www.scopus.com/inward/record.url?scp=84981717338&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84981717338&partnerID=8YFLogxK

U2 - 10.1117/12.2217131

DO - 10.1117/12.2217131

M3 - Conference contribution

AN - SCOPUS:84981717338

VL - 9784

BT - Medical Imaging 2016

A2 - Styner, Martin A.

A2 - Angelini, Elsa D.

A2 - Angelini, Elsa D.

PB - SPIE

ER -