Retinal Vascular Image Segmentation Using Genetic Algorithm Plus FCM Clustering

Those retinal vascular image without regular background and fixed contrast, make conventional approaches hard to achieve a satisfactory partition. So this paper presents a novel segmentation algorithm -- combination of genetic algorithms and FCM fuzzy clustering algorithms. First genetic algorithm is used to obtain the approximate solution of the global optimal solution. Then the approximate solution is used as the initial value of the FCM algorithm, FCM algorithm further is used for global optimum. Experimental results show that the algorithm is effective in performing retinal vascular image segmentation using morphological filtering.