A user-specific and selective multimodal biometric fusion strategy by ranking subjects

作者：

Highlights：

• We propose a user-specific and selective fusion for combining multiple biometric traits

• We develop a criterion called B-ratio that ranks subjects based on their match score statistics

• For some users, only a subset of the available traits are required for fusion

• Compared to conventional fusion, the proposed method can achieve similar or better performance at reduced computational cost

摘要

Highlights•We propose a user-specific and selective fusion for combining multiple biometric traits•We develop a criterion called B-ratio that ranks subjects based on their match score statistics•For some users, only a subset of the available traits are required for fusion•Compared to conventional fusion, the proposed method can achieve similar or better performance at reduced computational cost

论文关键词：Biometrics,Multibiometrics,Fusion,Doddington's Zoo,User-specific fusion,Client specific fusion

论文评审过程：Received 5 October 2012, Revised 28 February 2013, Accepted 22 March 2013, Available online 6 April 2013.

论文官网地址：https://doi.org/10.1016/j.patcog.2013.03.018