PCA-Based Face Recognition in Infrared Imagery: Baseline and Comparative Studies

  • Authors:
  • Xin Chen;Patrick J. Flynn;Kevin W. Bowyer

  • Affiliations:
  • -;-;-

  • Venue:
  • AMFG '03 Proceedings of the IEEE International Workshop on Analysis and Modeling of Faces and Gestures
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

Techniques for face recognition generally fall into global andlocal approaches, with the principal component analysis (PCA) beingthe most prominent global approach. This paper uses the PCAalgorithm to study the comparison and combination of infrared andtypical visible-light images forface recognition. This studyexamines the effects of lighting change, facial expression changeand passage of time between the gallery image and probe image.Experimental results indicate that when there is substantialpassage oftime (greater than one week) between the gallery andprobe images, recognition from typical visible-light images mayoutperform that from infrared images. Experimental results alsoindicate that the combination of the two generally out-performseither one alone. This is the only study that we know of to focuson the issue of how passage of time affects infrared facerecognition.