Fusion of fingerprint and iris biometrics using binary ant colony optimization

Abstract

This paper presents an effective method for decision level fusion of fingerprint and iris biometrics using binary ant colony optimization (ACO) technique to identify the imposter instances. ACO is an evolutionary method. The selection of a proper set of optimization parameters for ACO is a multi-objective decision making optimization problem. Initially the matching scores for individual biometric classifiers are computed. Next, a ACO-based procedure is followed to simultaneously optimize the parameters and the fusion rules for fingerprint and iris biometrics. The proposed method has been found to perform satisfactorily on several benchmark datasets.