Model-based illumination correction in retinal images

E. Grisan; A. Giani; E. Ceseracciu; A. Ruggeri

doi:10.1109/ISBI.2006.1625085

Model-based illumination correction in retinal images

E. Grisan, A. Giani, E. Ceseracciu, A. Ruggeri

University of Padua

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

35 Citations (Scopus)

Abstract

Retinal images are routinely acquired and assessed to provide diagnostic evidence for many important diseases. Because of the acquisition process, very often these images are non-uniformly illuminated and exhibit local luminosity and contrast variability. This problem may seriously affect the diagnostic process and its outcome, especially if an automatic computer-based procedure is used. We propose here a new method to estimate and correct luminosity variation in retinal images. The method uses the hue, saturation, value (HSV) colour space to better decouple the luminance and chromatic information. Then, it fits an illumination model on a proper subregion (the retinal background) of the saturation and value channels. This solves many of the drawbacks of previously proposed methods, as filter-based correction which fails when large lesions or retinal features are present.

Original language	English
Title of host publication	2006 3rd IEEE International Symposium on Biomedical Imaging
Subtitle of host publication	From Nano to Macro - Proceedings
Pages	984-987
Number of pages	4
DOIs	https://doi.org/10.1109/ISBI.2006.1625085
Publication status	Published - 8 May 2006
Externally published	Yes
Event	2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Arlington, VA, United States Duration: 6 Apr 2006 → 9 Apr 2006

Publication series

Name	2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings
Volume	2006

Conference

Conference	2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro
Country/Territory	United States
City	Arlington, VA
Period	6/04/06 → 9/04/06

Access to Document

10.1109/ISBI.2006.1625085

Cite this

Grisan, E., Giani, A., Ceseracciu, E., & Ruggeri, A. (2006). Model-based illumination correction in retinal images. In 2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings (pp. 984-987). Article 162585 (2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings; Vol. 2006). https://doi.org/10.1109/ISBI.2006.1625085

@inproceedings{ed5c35d7321143c4be4ec4a3f62789cd,

title = "Model-based illumination correction in retinal images",

abstract = "Retinal images are routinely acquired and assessed to provide diagnostic evidence for many important diseases. Because of the acquisition process, very often these images are non-uniformly illuminated and exhibit local luminosity and contrast variability. This problem may seriously affect the diagnostic process and its outcome, especially if an automatic computer-based procedure is used. We propose here a new method to estimate and correct luminosity variation in retinal images. The method uses the hue, saturation, value (HSV) colour space to better decouple the luminance and chromatic information. Then, it fits an illumination model on a proper subregion (the retinal background) of the saturation and value channels. This solves many of the drawbacks of previously proposed methods, as filter-based correction which fails when large lesions or retinal features are present.",

author = "E. Grisan and A. Giani and E. Ceseracciu and A. Ruggeri",

year = "2006",

month = may,

day = "8",

doi = "10.1109/ISBI.2006.1625085",

language = "English",

isbn = "0780395778",

series = "2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings",

pages = "984--987",

booktitle = "2006 3rd IEEE International Symposium on Biomedical Imaging",

note = "2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro ; Conference date: 06-04-2006 Through 09-04-2006",

}

Grisan, E, Giani, A, Ceseracciu, E & Ruggeri, A 2006, Model-based illumination correction in retinal images. in 2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings., 162585, 2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings, vol. 2006, pp. 984-987, 2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Arlington, VA, United States, 6/04/06. https://doi.org/10.1109/ISBI.2006.1625085

Model-based illumination correction in retinal images. / Grisan, E.; Giani, A.; Ceseracciu, E. et al.
2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings. 2006. p. 984-987 162585 (2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings; Vol. 2006).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Model-based illumination correction in retinal images

AU - Grisan, E.

AU - Giani, A.

AU - Ceseracciu, E.

AU - Ruggeri, A.

PY - 2006/5/8

Y1 - 2006/5/8

N2 - Retinal images are routinely acquired and assessed to provide diagnostic evidence for many important diseases. Because of the acquisition process, very often these images are non-uniformly illuminated and exhibit local luminosity and contrast variability. This problem may seriously affect the diagnostic process and its outcome, especially if an automatic computer-based procedure is used. We propose here a new method to estimate and correct luminosity variation in retinal images. The method uses the hue, saturation, value (HSV) colour space to better decouple the luminance and chromatic information. Then, it fits an illumination model on a proper subregion (the retinal background) of the saturation and value channels. This solves many of the drawbacks of previously proposed methods, as filter-based correction which fails when large lesions or retinal features are present.

AB - Retinal images are routinely acquired and assessed to provide diagnostic evidence for many important diseases. Because of the acquisition process, very often these images are non-uniformly illuminated and exhibit local luminosity and contrast variability. This problem may seriously affect the diagnostic process and its outcome, especially if an automatic computer-based procedure is used. We propose here a new method to estimate and correct luminosity variation in retinal images. The method uses the hue, saturation, value (HSV) colour space to better decouple the luminance and chromatic information. Then, it fits an illumination model on a proper subregion (the retinal background) of the saturation and value channels. This solves many of the drawbacks of previously proposed methods, as filter-based correction which fails when large lesions or retinal features are present.

U2 - 10.1109/ISBI.2006.1625085

DO - 10.1109/ISBI.2006.1625085

M3 - Conference contribution

AN - SCOPUS:33750945833

SN - 0780395778

SN - 9780780395770

T3 - 2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings

SP - 984

EP - 987

BT - 2006 3rd IEEE International Symposium on Biomedical Imaging

T2 - 2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro

Y2 - 6 April 2006 through 9 April 2006

ER -