A spectral independent approach for physiological and geometric based face recognition in the visible, middle-wave and long-wave infrared bands

作者：

Highlights：

• Propose new automated tri-spectral (visible, MWIR and LWIR) FR approach

• Design experiments to quantitatively measure benefits of global vs. local matchers

• Evaluation of global vs. local based matchers when fused at the score level

• Achieve rank-1 identification rate of at least 99.43% per spectrum of operation

摘要

•Propose new automated tri-spectral (visible, MWIR and LWIR) FR approach•Design experiments to quantitatively measure benefits of global vs. local matchers•Evaluation of global vs. local based matchers when fused at the score level•Achieve rank-1 identification rate of at least 99.43% per spectrum of operation

论文关键词：Face recognition,Visible,Middle-wave infrared,Long-wave infrared,Fiducial point extraction and matching

论文评审过程：Received 11 April 2013, Revised 5 February 2014, Accepted 26 June 2014, Available online 21 July 2014.

论文官网地址：https://doi.org/10.1016/j.imavis.2014.06.010