On designing practical long range near infrared-based face recognition systems
作者:
Highlights:
• Used a set of unique multi-scenario challenging face datasets.
• Dealt with visible/NIR, variable distance, indoors/outdoors, day/night face data.
• Solutions to practical FR scenarios, including same and cross spectral matching.
• Developed an in-house novel solution to intra/cross-distance NIR FR problems.
• Performance of our face matching solution is compared to the state-of-the-art.
摘要
•Used a set of unique multi-scenario challenging face datasets.•Dealt with visible/NIR, variable distance, indoors/outdoors, day/night face data.•Solutions to practical FR scenarios, including same and cross spectral matching.•Developed an in-house novel solution to intra/cross-distance NIR FR problems.•Performance of our face matching solution is compared to the state-of-the-art.
论文关键词:Forensics,Face recognition,Near infrared,Cross-scenario face matching,Demographic information,Night-time,Long-distance,Score level fusion
论文评审过程:Received 14 February 2014, Revised 25 December 2015, Accepted 24 April 2016, Available online 4 May 2016, Version of Record 26 May 2016.
论文官网地址:https://doi.org/10.1016/j.imavis.2016.04.013