An Efficient Dual Stage Approach for Iris Feature Extraction Using Interest Point Pairing

Abstract

This paper proposes a novel feature extraction and matching technique for iris recognition using interest points. The feature set comprises of spatial location of corner points and entropy information of the window around the corner. Corner matching is an elementary problem that is resolved using dual stage approach. At first stage the potential corners are obtained by finding Euclidean distance between spatial coordinates. These potential corners are used to find actual corners based on their affinity around a window, which is measured using mutual information (MI). For the purpose of evaluating experimental results three different datasets i.e., BATH, CASIA and IITK are used. The proposed dual stage approach has accuracy more than 98% with FRR of 0.0% and FAR of 2.61%.