Efficient extraction of consistent bit locations from binarized iris features

作者：

Highlights：

• An efficient framework for extracting consistent bits from IrisCodes is proposed.

• A criteria (t-consistency) is defined for quantifying the stability of IrisCodes.

• Use of information from iris masks mitigates effects of noise on extracted bits.

• Extensive empirical results have been validated on two benchmark iris databases.

摘要

•An efficient framework for extracting consistent bits from IrisCodes is proposed.•A criteria (t-consistency) is defined for quantifying the stability of IrisCodes.•Use of information from iris masks mitigates effects of noise on extracted bits.•Extensive empirical results have been validated on two benchmark iris databases.

论文关键词：Biometrics,IrisCode,Consistency,Clustering

论文评审过程：Received 15 May 2019, Revised 13 August 2019, Accepted 17 August 2019, Available online 19 August 2019, Version of Record 23 August 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.112884