Detecting blood vessels is useful in medical diagnosis for the purpose of detecting many diseases. Gabor filter in one of the most important methods used in automated detection of blood vessels in digital retinal images, therefore, improving its response is highly desirable. This filter has many parameters that govern its response. This paper derives new parameters to optimise the sensitivity of the Gabor filter using Genetic Algorithms (GAs). The experiments were performed on the test set of the Digital Retinal Images for Vessel Detection (DRIVE) database. Several experiments were conducted to achieve better performance for Gabor filter: The area under the receiver operating curve (ROC) is used as a fitness function for the GAs. The results of the above experiments are compared with previous techniques to prove the effectiveness of the proposed method.
Track
CCAT: Communications and Computer Applications and Technologies
Conference
3rd Mosharaka International Conference on Communications, Computers and Applications (MIC-CCA 2009)
Congress
2009 Global Congress on Communications, Computers and Applications (GC-CCA 2009), 26-28 October 2009, Amman, Jordan
Pages
48-55
Topics
Artificial Intelligence Genetic Algorithms
ISSN
2227-331X
DOI
BibTeX
@inproceedings{388CCA2009,
title={Improved Detection of Blood Vessels from Digital Retinal Images Using optimised Gabor Filter},
author={Heyam Bader, and Mousa T. Al Akhras, and Abdel Latif Abu Dalhoum},
booktitle={2009 Global Congress on Communications, Computers and Applications (GC-CCA 2009)},
year={2009},
pages={48-55},
doi={}},
organization={Mosharaka for Research and Studies}
}
