Automatic Detection of Blood Vessels in Digital Retinal Images using Soft Computing Technique

Abstract Insulin-dependent mortals (humans) are attributed by blemished (defective) metabolism of glycogen (glucose) that leads to long lasting dysfunction and damage of an organ. The most prosaic (common) obstacle (complication) of diabetes is Diabetic Retinopathy, which is one of the predominant (primary) root of visual death and visual impairment in middle aged patient. The expeditious (rapid) mutation of diabetes patient thrust the limitations of the present Diabetic Retinopathy Screening potential for which the digital visualize of eye ball fundus can provide a potential solution by an automated image analysis algorithm. The present learning focus is developing the extraction of normal and isolated characteristics or marks in colour retinal images. The adaptive filters are tuned to match the lump (part) of vessel to be extracted in green channel images. To classify the pixels into vessels and non-vessels the Biogeography Based Optimization Algorithm is applied.