Pruning optimum-path forest ensembles using quaternion-based optimization
In this paper we propose a method using a generalization of the weighted majority voting scheme to locate the optic disc (OD) in retinal images automatically. The location with the maximal sum of the weights of OD center candidates falling into a disc of radius predefined in the clinical protocol is chosen for optic disc. We have worked out a weighted voting scheme, where besides the weights, an additional (e.g. geometrical) condition have to be taken into account in making the final decision. We can achieve better overall performance with this generalized weighted voting system than with the weighted majority voting and each individual algorithm.