Evaluation of multimodal biometrics at different levels of face and palm print fusion schemes

Abstract

Background: Presently much attention is being paid to biometrics in the user authentication system, because multimodal is considered an accurate method to achieve higher degree of accuracy. Multimodal systems always give enhanced performance compared to unimodal. Methodology: The present study evaluated the performance of multimodal system by applying fusing face and palm print biometrics. Different levels of fusion schemes with optimal strategies were employed and the performance was evaluated over the all levels. Results: Overall, the best results of multimodal were obtained at the score level fusion by applying AND rule as 91 at 0.01% FAR, 94.5 at 0.1% FAR and 97.5 at 1.0% FAR. Whereas the best results of unimodal system were 42 at 0.01% FAR, 68 at 0.1% FAR and 84.75 at 1.0% FAR obtained with palmprint. The study showed that by fusing multimodal biometrics, a higher level of verification can be achieved. Conclusion: From the experimental results, it can be found that score level fusion with sum rules is reliable and feasible method for fusion of face and palmprint.