Robust Blood Vessel Segmentation Algorithm for Fundus Images


Salih, Nbhan D. and Saleh, Marwan D. (2021) Robust Blood Vessel Segmentation Algorithm for Fundus Images. In: 2021 6th IEEE International Conference on Recent Advances and Innovations in Engineering (ICRAIE), 1-3 Dec 2021, Kedah, Malaysia.

[img] Text
Robust_Blood_Vessel.pdf - Published Version
Restricted to Repository staff only

Download (1MB)


Diabetic retinopathy (DR) is a vision threatening in which damage occurs to the retina due to diabetes mellitus. There is a greater need for automated techniques for quick screening of DR due to the increasing number of patients. The accurate diagnosis of DR depends upon detecting and analyzing some features of human retina (i.e. blood vessels, fovea, optic disc, etc.) as well as several types of spot lesions (i.e. exudates, drusen, microaneurysms, hemorrhage, etc). This study focus on blood vessel segmentation in the human retina, which is an essential milestone in the analysis of retinal images. With the proposed algorithm, a few image-processing techniques for contrast enhancement, normalization and thresholding, are used to achieve more efficient and optimized segmentation. The results of the experiments demonstrate that the presented algorithm produces high-accuracy segmentation and the algorithm is ideally suited for real-time screening applications and large data retrieval.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Diabetic Retinopathy, Image Processing, Fundus Images, Vessel segmentation, Automatic Thresholding
Subjects: Q Science > QC Physics > QC350-467 Optics. Light
Divisions: Faculty of Computing and Informatics (FCI)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 07 Oct 2022 03:08
Last Modified: 07 Oct 2022 03:08


Downloads per month over past year

View ItemEdit (login required)