PCA = Gabor for Expression Recognition
- Author(s): Dailey, Matthew N;
- Cottrell, Garrison W
- et al.
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.
Pre-2018 CSE ID: CS1999-0629