A deep learning based unified framework to detect, segment and recognize irises using spatially corresponding features

作者：

Highlights：

• A novel and unified deep learning based framework to automatically detect, segment and recognize irises from eye images.

• Higher iris detection and segmentation accuracy over previous approach.

• Outperforming results over other methods for iris recognition in the literature (e.g., ICCV 2017) using publicly accessible databases.

• Comparative experimental results using a range of promising iris recognition methods.

摘要

•A novel and unified deep learning based framework to automatically detect, segment and recognize irises from eye images.•Higher iris detection and segmentation accuracy over previous approach.•Outperforming results over other methods for iris recognition in the literature (e.g., ICCV 2017) using publicly accessible databases.•Comparative experimental results using a range of promising iris recognition methods.

论文关键词：Iris recognition,Deep learning,Spatially corresponding features

论文评审过程：Received 3 August 2018, Revised 31 December 2018, Accepted 9 April 2019, Available online 3 May 2019, Version of Record 11 May 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.04.010