Research Article Comparative Study of Multimodal Biometric Recognition by Fusion of Iris and Fingerprint Houda Benaliouche and Mohamed Touahria Computer Science Department, University of Ferhat Abbas S´ etif 1, Pˆ ole 2 - El Bez, 19000 S´ etif, Algeria Correspondence should be addressed to Houda Benaliouche; houda.aimar@gmail.com Received 28 August 2013; Accepted 17 November 2013; Published 29 January 2014 Academic Editors: J. Shu and F. Yu Copyright © 2014 H. Benaliouche and M. Touahria. Tis is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Tis research investigates the comparative performance from three diferent approaches for multimodal recognition of combined iris and fngerprints: classical sum rule, weighted sum rule, and fuzzy logic method. Te scores from the diferent biometric traits of iris and fngerprint are fused at the matching score and the decision levels. Te scores combination approach is used afer normalization of both scores using the min-max rule. Our experimental results suggest that the fuzzy logic method for the matching scores combinations at the decision level is the best followed by the classical weighted sum rule and the classical sum rule in order. Te performance evaluation of each method is reported in terms of matching time, error rates, and accuracy afer doing exhaustive tests on the public CASIA-Iris databases V1 and V2 and the FVC 2004 fngerprint database. Experimental results prior to fusion and afer fusion are presented followed by their comparison with related works in the current literature. Te fusion by fuzzy logic decision mimics the human reasoning in a sof and simple way and gives enhanced results. 1. Introduction Biometrics refers to identity verifcation of persons according to their physical or behavioral characteristics. Many physical body parts and personal features have been used for biometric systems: fngers, hands, feet, faces, irises, retinas, ears, teeth, veins, voices, signatures, typing styles, gaits, odors, and DNA. Person verifcation based on biometric features has attracted more attention in designing security systems [1]. However, no single biometrical feature can meet all the performance requirements in practical systems [2]. Most of biometric systems are far from satisfactory in terms of user confdence and user friendliness and have a high false rejection rate FRR. Tere is a need for development of novel paradigms and protocols and improved algorithms for human recognition. Unimodal biometric systems use one biometric trait to recognize individuals. Tese systems are far from perfect and sufer from several problems like noise, nonuniversality, lack of individuality, and sensitivity to attack. Multimodal biometric systems use multiple modalities to overcome the limitations that arise when using single biometric trait to recognize individuals. Multiple biometric systems perform better than unimodal biometric systems. Te use of only one biometric trait susceptible to noise, bad capture, and other inherent problems makes the unimodal biometric system unsuited for all applications. Many works in the literature have demonstrated that the drawbacks of the unimodal biometric systems are mainly genuine and imposters identifcation failure due to the intraclass variations and the interclass similarities, while the drawbacks associated with multimodal biometrics are increased complicity of the system with two or more sensors [2–6] and thus higher cost, as well as inconvenience of using several biometrics. So, identifcation of person with high accuracy and less complexity of the system is becoming critical in a number of security issues in our society. Iris and fngerprint biometrics are more simple, accurate, and reliable as compared to other available traits. Tese properties make their fusion particularly promising solution to the authentication problems today. Moreover, fusion of iris and fngerprint is more reliable than fusion of each one with another biometric like face [7]. However, iris biometric has more features and stability and resistance to attacks than fngerprint biometric; despite this, the conventional fusion Hindawi Publishing Corporation e Scientific World Journal Volume 2014, Article ID 829369, 13 pages http://dx.doi.org/10.1155/2014/829369