Blood vessel segmentation approach for extracting the vasculature on retinal fundus images using Particle Swarm Optimization

The early diagnosis of some diseases is one of the most important reasons for success of treatment and ensuring healing. In this paper, we present blood vessel segmentation approach for extracting the vasculature on retinal fundus images. Novel segmentation approach of retinal images is used based on the Particle Swarm Optimization (PSO) in order to determine the n - 1 optimal n-level thresholds on retinal fundus images. The proposed approach is tested on the DRIVE datasets and its efficiency is compared with alternative methods. The obtained results show that the proposed approach is effective and achieves average accuracy of 97.75% and best accuracy of 98.857%.