Automated positioning of overlapping eye fundus images

Abstract

Changes in eye fundus images can be associated with numerous vision threatening diseases such as glaucoma, optic neuropathy, swelling of the optic nerve head, or related to some systemic disease. Tracking the progress of a possible disease of the patient becomes very difficult from separated retinal images. In this article we present a method which registers two retinal images so that the fundus images overlaps each other in the best way. As a separate case, this article shows that in order to solve the optic nerve disc registration problem a linear transformation of retinal image is sufficient. A human identification possibility via retinal image registration will be disclosed as well. © 2008 Springer-Verlag Berlin Heidelberg.