ML Anthology

Learning Mappings for Face Synthesis from near Infrared to Visual Light Images

Jie Chen, Dong Yi, Jimei Yang, Guoying Zhao, Stan Z. Li, Matti Pietikäinen
CVPR 2009 pp. 156-163
doi:10.1109/CVPR.2009.5206832 /cvpr/2009/chen2009cvpr-learning/

Abstract

This paper deals with a new problem in face recognition research, in which the enrollment and query face samples are captured under different lighting conditions. In our case, the enrollment samples are visual light (VIS) images, whereas the query samples are taken under near infrared (NIR) condition. It is very difficult to directly match the face samples captured under these two lighting conditions due to their different visual appearances. In this paper, we propose a novel method for synthesizing VIS images from NIR images based on learning the mappings between images of different spectra (i.e., NIR and VIS). In our approach, we reduce the inter-spectral differences significantly, thus allowing effective matching between faces taken under different imaging conditions. Face recognition experiments clearly show the efficacy of the proposed approach.

CVPR Semantic Scholar

Cite

Text

Chen et al. "Learning Mappings for Face Synthesis from near Infrared to Visual Light Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2009. doi:10.1109/CVPR.2009.5206832

Markdown

[Chen et al. "Learning Mappings for Face Synthesis from near Infrared to Visual Light Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2009.](https://mlanthology.org/cvpr/2009/chen2009cvpr-learning/) doi:10.1109/CVPR.2009.5206832

BibTeX

@inproceedings{chen2009cvpr-learning,
  title     = {{Learning Mappings for Face Synthesis from near Infrared to Visual Light Images}},
  author    = {Chen, Jie and Yi, Dong and Yang, Jimei and Zhao, Guoying and Li, Stan Z. and Pietikäinen, Matti},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2009},
  pages     = {156-163},
  doi       = {10.1109/CVPR.2009.5206832},
  url       = {https://mlanthology.org/cvpr/2009/chen2009cvpr-learning/}
}