On improving the Performance of Multimodal biometric authentication through Ant colony optimization

Multimodal biometric authentication systems are now widely used for providing the utmost security owing to its better recognition performance compared to unimodal systems. Multimodal biometric systems are developed by combining the information of individual biometrics. In this paper, a multimodal biometric system is proposed by combining the scores of iris and palm print traits of a person. This information fusion takes place at the matching score level, due to the ease in accessing and combining the scores generated by the two different matchers. Since the matching scores output by the two modalities are heterogeneous, score normalization is needed to transform these scores into a common domain, prior to combining them. The normalized values are then applied to various score fusion methods. The resulting scores are compared to a threshold value for taking a decision of accepting or rejecting the person. The recognition accuracy of fusion methods strongly depend upon the correctness of this threshold value. Hence we propose Ant colony optimization (ACO) technique for selecting the optimal threshold value for each of the fusion method employed. This approach further enhances the accuracy of the system compared to the fusion methods with no optimal threshold. The experimental results obtained using CASIA iris and palm print databases show that the application of ACO results in higher recognition rates and lower error rates. To the best of our knowledge, it is the first work that applies ACO to enhance the accuracy of biometric authentication process. Key-Words: ACO, Biometrics, Multimodal, Normalization, Product, Score fusion, Sum