Retinal image registration from artery–venous subtree by graph theoretical characterization of retinal vascular network

There are many approaches exist in literature to register retinal images from their RGB fundus stages. Previous approaches need to take special care upon transformations like rotation and translation. In this paper, an image registration method has been proposed which is robust against transformation and does not need extra burden to handle it. In particular, our proposed approach consists of three major stages. At the first stage, vascular network has been segregated into many other coloured sub-categories on the segmented fundus image. The second stage is to find out arterial and venous segments among the coloured sub-categories of the network by following the proposed artery-vein (A/V) classification method. Finally, each arterial and venous segments are combined together to form arterial and venous subtrees which resembles a binary tree. Finding inorder traversal of each such subtrees complete the process for image registration. We evaluate the approach with ground truth images of a public database called RITE. The work shows an arterial-venous classification rate as \(89\%\) using an automated vessel segmented image as input which is comparable with other existing methods.