Binary feature fusion for discriminative and secure multi-biometric cryptosystems

作者：

Highlights：

• Propose a binary feature fusion approach for multi-biometric cryptosystems

• Agglomerative hierarchical clustering and within-group (cluster) fusion are used.

• Fused feature achieves both high discriminability and entropy.

• Trade-off between system matching accuracy and security is analyzed.

摘要

•Propose a binary feature fusion approach for multi-biometric cryptosystems•Agglomerative hierarchical clustering and within-group (cluster) fusion are used.•Fused feature achieves both high discriminability and entropy.•Trade-off between system matching accuracy and security is analyzed.

论文关键词：Biometric,Binary representation,Binary feature,Multi-biometric,Feature fusion,Template protection,Cryptosystems

论文评审过程：Received 13 November 2015, Revised 8 September 2016, Accepted 16 November 2016, Available online 24 November 2016, Version of Record 20 February 2017.

论文官网地址：https://doi.org/10.1016/j.imavis.2016.11.011