Face synthesis from near-infrared to visual light spectrum using quotient image and kernel-based multifactor analysis

  • Zeda Zhang*
  • , Yunhong Wang
  • , Zhaoxiang Zhang*
  • , Guangpeng Zhang
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper addresses the problem of synthesizing an artificial visual light (VIS) facial image from near-infrared (NIR) input. After extensively assessing photic characteristics of tissues at human skin surface, we propose a framework for this task. Firstly, we take the quotient images for training and reconstruction, so that information related to face structure can be preserved. Secondly, to handle heterogeneous blur resulted from multiple scattering within tissues, we introduce kernel-based strategy as a powerful nonlinear analyzing instrument. Finally, as in our application the image ensembles involve multiple factors, a tensor structure is employed to transform heterogeneous face data into uniform subspaces. Comparative results show that our synthesized images are both suited for human vision and discriminative for machine recognition.

Original languageEnglish
Title of host publicationElectronic Proceedings of the 2011 IEEE International Conference on Multimedia and Expo, ICME 2011
DOIs
StatePublished - 2011
Event2011 12th IEEE International Conference on Multimedia and Expo, ICME 2011 - Barcelona, Spain
Duration: 11 Jul 201115 Jul 2011

Publication series

NameProceedings - IEEE International Conference on Multimedia and Expo
ISSN (Print)1945-7871
ISSN (Electronic)1945-788X

Conference

Conference2011 12th IEEE International Conference on Multimedia and Expo, ICME 2011
Country/TerritorySpain
CityBarcelona
Period11/07/1115/07/11

Keywords

  • kernel-based multifactor analysis
  • near-infared
  • quotient image
  • synthesis
  • visual light

Fingerprint

Dive into the research topics of 'Face synthesis from near-infrared to visual light spectrum using quotient image and kernel-based multifactor analysis'. Together they form a unique fingerprint.

Cite this