Improving Biometric Identification Through Score Level Face Fingerprint Fusion

Multi-modal biometric fusion is more accurate and reliable compared to recognition using a single biometric modality. However, most existing fusion approaches neglect the influence of the qualities of the biometric samples in information fusion. Our goal is to advance the state-of-the-art in biometric fusion technology by providing a more universal and more accurate solution for personal identification and verification with predictive quality metrics. In this work, we developed score-level multi-modal fusion algorithms based on predictive quality metrics and employed them for the task of face and fingerprint biometric fusion. Score level fusion is commonly preferred in multimodal biometric systems because matching scores contain sufficient information to make genuine and impostor case distinguishable and they are relatively easy to obtain. In this paper the performance of sum rule-based score level fusion are examined. Before fusion of sum rule, normalization is done by using any one technique like min-max normalization, z score normalization and tanh estimator's normalization. In this paper min max normalization is used for normalization.