Zhejiang Hexin Flush Network Services Ltd
Remarkable improvements in recognition can be achieved through multi-biometric fusion. Among various fusion techniques, score level fusion is the most frequently used in multi-biometric system. In this paper, the authors propose a novel fusion algorithm based on False Reject Rate (FRR) and False Accept Rate (FAR) using Support Vector Machine (SVM). It transfers scores into corresponding FRRs and FARs, thus avoiding calculating posteriori probability of a certain score, as well as be capable of illustrating distribution of matching scores.