Probability map based localization of optic disk

Attila Budai, Lenke Laurik, Joachim Hornegger, G. M. Somfai, Georg Michelson

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

1 Citation (Scopus)

Abstract

Fundus imaging is one of themost commonly used modalities for examining retinal structures. The images are mostly analyzed by physicians. These diagnoses are subjective with a high rate of inter-observer variability, therefore an automated or a computer aided diagnosis is needed to speed up the monotonous screening process and to provide objective measurements. In this article we present an automatic algorithm for localization of the optic disk center in fundus images. The application field of the algorithm is preprocessing for further algorithms such as segmentation of the optic disk boundary, vessel tracking etc. The algorithm is evaluated using the DRIVE database and our own public high resolution image database. The tests show a localization error less than 0.2 optic disk diameter (ODD) in case of the high resolution database, and less than 0.35 ODD in case of the lower resolution DRIVE database.

Original languageEnglish
Title of host publication2012 19th International Conference on Systems, Signals and Image Processing, IWSSIP 2012
Pages568-571
Number of pages4
Publication statusPublished - 2012
Event2012 19th International Conference on Systems, Signals and Image Processing, IWSSIP 2012 - Vienna, Austria
Duration: Apr 11 2012Apr 13 2012

Other

Other2012 19th International Conference on Systems, Signals and Image Processing, IWSSIP 2012
CountryAustria
CityVienna
Period4/11/124/13/12

Fingerprint

Optics
Optical resolving power
Computer aided diagnosis
Image resolution
Screening
Imaging techniques

Keywords

  • Fundus Imaging
  • Optic disk localization
  • Vessel segmentation

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Budai, A., Laurik, L., Hornegger, J., Somfai, G. M., & Michelson, G. (2012). Probability map based localization of optic disk. In 2012 19th International Conference on Systems, Signals and Image Processing, IWSSIP 2012 (pp. 568-571). [6208205]

Probability map based localization of optic disk. / Budai, Attila; Laurik, Lenke; Hornegger, Joachim; Somfai, G. M.; Michelson, Georg.

2012 19th International Conference on Systems, Signals and Image Processing, IWSSIP 2012. 2012. p. 568-571 6208205.

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

Budai, A, Laurik, L, Hornegger, J, Somfai, GM & Michelson, G 2012, Probability map based localization of optic disk. in 2012 19th International Conference on Systems, Signals and Image Processing, IWSSIP 2012., 6208205, pp. 568-571, 2012 19th International Conference on Systems, Signals and Image Processing, IWSSIP 2012, Vienna, Austria, 4/11/12.
Budai A, Laurik L, Hornegger J, Somfai GM, Michelson G. Probability map based localization of optic disk. In 2012 19th International Conference on Systems, Signals and Image Processing, IWSSIP 2012. 2012. p. 568-571. 6208205
Budai, Attila ; Laurik, Lenke ; Hornegger, Joachim ; Somfai, G. M. ; Michelson, Georg. / Probability map based localization of optic disk. 2012 19th International Conference on Systems, Signals and Image Processing, IWSSIP 2012. 2012. pp. 568-571
@inproceedings{7e2509e38bab45d0bb55ca94d6aaad03,
title = "Probability map based localization of optic disk",
abstract = "Fundus imaging is one of themost commonly used modalities for examining retinal structures. The images are mostly analyzed by physicians. These diagnoses are subjective with a high rate of inter-observer variability, therefore an automated or a computer aided diagnosis is needed to speed up the monotonous screening process and to provide objective measurements. In this article we present an automatic algorithm for localization of the optic disk center in fundus images. The application field of the algorithm is preprocessing for further algorithms such as segmentation of the optic disk boundary, vessel tracking etc. The algorithm is evaluated using the DRIVE database and our own public high resolution image database. The tests show a localization error less than 0.2 optic disk diameter (ODD) in case of the high resolution database, and less than 0.35 ODD in case of the lower resolution DRIVE database.",
keywords = "Fundus Imaging, Optic disk localization, Vessel segmentation",
author = "Attila Budai and Lenke Laurik and Joachim Hornegger and Somfai, {G. M.} and Georg Michelson",
year = "2012",
language = "English",
isbn = "9783200023284",
pages = "568--571",
booktitle = "2012 19th International Conference on Systems, Signals and Image Processing, IWSSIP 2012",

}

TY - GEN

T1 - Probability map based localization of optic disk

AU - Budai, Attila

AU - Laurik, Lenke

AU - Hornegger, Joachim

AU - Somfai, G. M.

AU - Michelson, Georg

PY - 2012

Y1 - 2012

N2 - Fundus imaging is one of themost commonly used modalities for examining retinal structures. The images are mostly analyzed by physicians. These diagnoses are subjective with a high rate of inter-observer variability, therefore an automated or a computer aided diagnosis is needed to speed up the monotonous screening process and to provide objective measurements. In this article we present an automatic algorithm for localization of the optic disk center in fundus images. The application field of the algorithm is preprocessing for further algorithms such as segmentation of the optic disk boundary, vessel tracking etc. The algorithm is evaluated using the DRIVE database and our own public high resolution image database. The tests show a localization error less than 0.2 optic disk diameter (ODD) in case of the high resolution database, and less than 0.35 ODD in case of the lower resolution DRIVE database.

AB - Fundus imaging is one of themost commonly used modalities for examining retinal structures. The images are mostly analyzed by physicians. These diagnoses are subjective with a high rate of inter-observer variability, therefore an automated or a computer aided diagnosis is needed to speed up the monotonous screening process and to provide objective measurements. In this article we present an automatic algorithm for localization of the optic disk center in fundus images. The application field of the algorithm is preprocessing for further algorithms such as segmentation of the optic disk boundary, vessel tracking etc. The algorithm is evaluated using the DRIVE database and our own public high resolution image database. The tests show a localization error less than 0.2 optic disk diameter (ODD) in case of the high resolution database, and less than 0.35 ODD in case of the lower resolution DRIVE database.

KW - Fundus Imaging

KW - Optic disk localization

KW - Vessel segmentation

UR - http://www.scopus.com/inward/record.url?scp=84863946233&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863946233&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9783200023284

SP - 568

EP - 571

BT - 2012 19th International Conference on Systems, Signals and Image Processing, IWSSIP 2012

ER -