Abstract—Diabetic retinopathy is caused by complications of
diabetes, which can eventually lead to blindness. As new blood
vessels form at the back of the eye as a part of diabetic
retinopathy (DR), they can bleed and blur vision. Detection of
these new vessels and their structure in retinal images is very
important for diagnosis of diabetic retinopathy. In this paper
two different techniques have been compared. First technique
uses Gaussian filtering for preprocessing, LoG filtering for
enhancement and adaptive thresholding for segmentation
purpose. Second technique uses unsharp masking for
preprocessing, Gabor wavelet for enhancement and global
thresholding for segmentation. The performance of these
systems is evaluated on publicly available DRIVE and STARE
databases of manually labeled images. Experimental results
show that Gabor wavelet method gives best results for vessel
enhancement and global threshold gives good results for vessel
segmentation in retinal images.
Index Terms—Blood vessel, DIABETIC retinopathy (DR),
retinal images, unsharp masking, gabor wavelet transform,
adaptive thresholding, log filtering, enhancement,
segmentation.
The authors are with the Department of Software Engineering, Fatima
Jinnah Women University, Rawalpindi, Pakistan (e-mail:
safia_shabbir@hotmail.com, anam.tariq86@gmail.com,
usmakram@gmail.com).
[PDF]
Cite:Safia Shabbir, Anam Tariq, and M. Usman Akram, "A Comparison and Evaluation of Computerized Methods
for Blood Vessel Enhancement and Segmentation in
Retinal Images," International Journal of Future Computer and Communication vol. 2, no. 6, pp. 600-603, 2013.