A Fast Iris Location Based on Aggregating Gradient Approximation Using QMA-OWA Operator

A very robust biometric for the identification of humans is Iris Recognition. In order to recognize the Iris the determination of its exact location is required. The contemporary localization approaches, although accurate, often require a very long calculation. This paper presents an Iris Location method that is both accurate and fast. The approach relies on the detection of circular boundaries under an approach of gradient analysis in points of interest of successive arcs. The quantified majority operator QMA-OWA[20] was used in order to obtain a representative value for each successive arc. The identification of the Iris circular boundary in an image portion will be given by obtaining the arc with the greatest representative value. Thus, a fast algorithm of identification of circular boundaries is obtained from an aggregation process, guided by the linguistic quantifier many. The experimentation was developed upon the image database CASIA-IrisV3.