Nighttime face recognition at large standoff: Cross-distance and cross-spectral matching

作者：

Highlights：

• An imaging system designed to collect NIR and VIS face images at large standoffs.

• A general framework for cross-spectral and cross-distance face matching.

• A novel image restoration method that greatly improves low-quality face images.

• Our method significantly outperforms the state-of-the-art in three scenarios.

摘要

Highlights•An imaging system designed to collect NIR and VIS face images at large standoffs.•A general framework for cross-spectral and cross-distance face matching.•A novel image restoration method that greatly improves low-quality face images.•Our method significantly outperforms the state-of-the-art in three scenarios.

论文关键词：Nighttime face recognition,Heterogeneous face matching,Cross-distance matching,Cross-spectral matching,Image restoration,K-means clustering,Locally Linear Embedding (LLE)

论文评审过程：Received 4 September 2013, Revised 3 March 2014, Accepted 9 June 2014, Available online 17 June 2014.

论文官网地址：https://doi.org/10.1016/j.patcog.2014.06.004