Human eye iris recognition using the mutual information
Abstract:This article presents the new biometric electro-optical measuring method supported by PC for identification of a person by its eye iris image recognition. The aim of this approach is to show the ability of mutual information to such recognition. Couples of the comparative human iris images were geometrically aligned by maximization of their mutual information and subsequently recognized. The mutual information was estimated using the efficient algorithm proposed by G. A. Darbellay and I. Vajda. The decision whether two compared iris images belong to the same eye depends on the chosen threshold of the mutual information. Only a simple preprocessing of the iris images is needed to acquire their characteristic geometric parameters before the recognition is performed. The investigations carried out showed the correct (successful) personal identification better than 99%.
Document Type: Research Article
Affiliations: 1: Computer Science Department, Faculty of Sciences, Palacký University, Svobody 26, Cz-77900, Olomouc, Czech Republic 2: Department of Experimental Physics, Faculty of Sciences, Palacký University, 17.listopadu 50a, Cz-77207, Olomouc, Czech Republic 3: Institute of Information Theory and Automation, Academy of Sciences of the Czech Republic, Pod vodárenskou věží 4, PO Box 18, Cz-182 08 Prague 8, Czech Republic 4: Department of Experimental Physics, Faculty of Sciences, Palacký University, and Joint Laboratory of Optics of Palacký University and Academy of Sciences of the Czech Republic, 17.listopadu 50a, Cz-77207, Olomouc, Czech Republic
Publication date: November 1, 2004