PCA = Gabor for Expression Recognition

  • Authors:
  • Matthew N. Dailey;Garrison W. Cottrell

  • Affiliations:
  • -;-

  • Venue:
  • PCA = Gabor for Expression Recognition
  • Year:
  • 1999

Quantified Score

Hi-index 0.00

Visualization

Abstract

We show that Gabor filter representations give quantitatively indistinguishable results for classification of facial expressions as local PCA representations, in contrast to other recent work. We also show that a simple discriminant analysis automatically locates regions roughly corresponding to relevant Facial Actions. Finally, we in troduce a method that typically boosts generalization performance 9% by "peeking" at all of the unlabeled training patt erns before classifying them.