Optimal weight of the score level multiple biometric feature fusion
Zhou Yongguan · Journal of Tsinghua University(Science and Technology) · 2008
This paper describes an optimal weighting strategy for improving the performance of recognition systems by emphasizing the score level fusion of multimodal biometrics. The system uses a score normalization model which predigests the fusion strategy research. Then, a weighted combination of three parameters (false acceptance rate (FAR), false rejection rate (FRR), equal error rate (EER)) is minimized to give the best recognition result. Tests using palm prints as an example, show the effectiveness of score level fusion for promoting the performance of recognition systems.