Found a good match: Should I keep searching? — Accuracy and performance in iris matching using 1-to-First search
作者：
Highlights：
• Our work investigates the accuracy effects of 1:First search, comparing it with 1:N search.
• Experiments are performed in closed- and open-sets, various gallery sizes, with two iris matchers.
• Results show that this method causes large degradation in iris recognition accuracy rates.
• Accuracy degradation is bound to the gallery size and accuracy target.
• Careful threshold selection may allow the use of 1:First with minimal consequences to accuracy.
摘要
•Our work investigates the accuracy effects of 1:First search, comparing it with 1:N search.•Experiments are performed in closed- and open-sets, various gallery sizes, with two iris matchers.•Results show that this method causes large degradation in iris recognition accuracy rates.•Accuracy degradation is bound to the gallery size and accuracy target.•Careful threshold selection may allow the use of 1:First with minimal consequences to accuracy.
论文关键词：Biometrics,Iris recognition,Error rates,Identification,Accuracy,Search,1:First,1:N,Open-set
论文评审过程：Received 15 September 2017, Revised 15 January 2018, Accepted 16 March 2018, Available online 27 March 2018, Version of Record 18 April 2018.
论文官网地址：https://doi.org/10.1016/j.imavis.2018.03.003
