Paper Details

[ Downloads: 1 | Abstract Viewed: 500 | Pages: 5 ]

Abstract of the Article

Note: English CIVILICA is in its Trial Period so Full Texts can not be provided! Persian users can download it here

Vessel detection in retinal images using Radon transform and genetic algorithm

Authors:

[ Adel Ghazikhani ] - PhD student, Computer Engineering Department, Ferdowsi University of Mashhad, Iran
[ Hamidreza Pourreza ] - Associate Professor, Computer Engineering Department, Ferdowsi University of Mashhad, Iran

Abstract:

We propose a novel algorithm for vessel detection in retinal images. The proposed algorithm incorporates Radon Transform(RT) and Genetic Algorithm(GA) to detect vessels. We use RT because vessels could be approximated accurately by sets of lines. Since retinal images contain vessels of different size and width RT is performed locally. The local RT has parameters that should be set manually or automatically.We use GA to optimize the parameters of RT automatically. Our algorithm has been evaluated and compared with a similar algorithm using a standard dataset. The results show improvements in vessel detection.

Keywords:

Radon transform, Genetic algorithm, vessel detection, retinal images