We describe a multi-stage method to automatically locate features
on the human face. The method is coarse-to-fine. First a face
detector is applied to find the approximate scale and location of
the face in the image. Then individual feature detectors are
applied and the responses combined using a novel pairwise
probabilistic voting method. The points predicted by this method
are then refined using a version of the Active Appearance Model
(AAM) search, which is tuned to edge and corner features. The
final output of the three stage algorithm is shown to give much
better results than any other combination of methods. The method
outperforms previous published results on the BIOID test set.