Automated extraction of blood vessels in retinal images using rolling guidance filter
by Deepak Kumar Maharana; Pranati Das
International Journal of Biomedical Engineering and Technology (IJBET), Vol. 45, No. 1, 2024

Abstract: This paper represents an unsupervised approach for the segmentation of the retinal vasculatures in an instinctive way. In this approach, first, the ophthalmoscope images are enhanced by contrast stretching along with logarithmic transformation and contrast limited adaptive histogram equalisation (CLAHE). Next, the edges of the enhanced images are preserved by using a rolling guidance filter, and, subsequently, the residual image is obtained by the subtraction of the rolling guidance image from the CLAHE image. After that, the optic disk is excluded to give a better segmentation result. Next, the ISODATA thresholding method is applied to obtain the binary image. Finally, morphological operation with noise removal and the boundary is excluded to obtain the final segmented image. The presented approach's performance is appraised using different mathematical measures. It achieves average false positive rate (FPR), true positive rate (TPR) and accuracy of 0.0152, 0.7037 and 0.9604 for DRIVE database and 0.0313, 0.776 and 0.9541 for STARE database.

Online publication date: Thu, 16-May-2024

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Biomedical Engineering and Technology (IJBET):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com