Vessel extraction in retinal images using multilevel line detection

This paper presents an algorithm to segment the blood vessels in retinal images. The contribution of this work is that we exhibit how a line detection can be applied in a multi-scale framework to fulfill the sophisticated task of vessel segmentation. The key idea of our algorithm is to systematically combine the outputs of Gaussian based line detection that is applied sequentially to the input image at several scales from coarse to fine levels. This brings down to the strategy that the evidences of larger size vessels are used to steer the process of addition of smaller vessels. Our proposed method is evaluated on the public DRIVE database and shows results with false positive rate.