Bimodal Biometric Person Recognition by Score Fusion

In this paper, an optimization method, Golden Ratio Algorithm (GRA), is introduced for biometric fusion at score level. Some experiments have been conducted, and the results show that the proposed method can optimally balance the contributions of different modalities for biometric person recognition. And the test results have also indicated that an Audio-Visual (AV) bimodal biometric system normally outperforms the respective single modality systems when biometric fusion is done properly. Furthermore, the experiments demonstrate that the performance of a biometric system relies on the accurate extraction of features from original biometric sources.