Retinal Blood Vessel Segmentation by Employing Various Upgraded Median Filters

Retinal image analysis plays a vital part in diagnosis of Diabetic Retinopathy. It is a progressive disease and leads to blindness which can be prevented if detected at the earlier stage. In this paper, a robust method of blood tree segmentation is proposed by using some advanced median filters such as improved median, hybrid median and weighted median filters. The algorithm for vessel extraction is carried out in three different stages: preprocessing, extraction of blood vessel, and post processing. The results are compared with the median filter segmentation approach. The approach is validated on DRIVE database. The suggested method delivers more accurate outputs than the median filter in terms of accuracy, sensitivity, and specificity.