Automatic facial expression recognition in real-time from dynamic sequences of 3D face scans

In this paper, we present a fully-automatic and real-time approach for person-independent recognition of facial expressions from dynamic sequences of 3D face scans. In the proposed solution, first a set of 3D facial land- marks are automatically detected, then the local characteris- tics of the face in the neighborhoods of the facial landmarks and their mutual distances are used to model the facial de- formation. Training two hidden Markov models for each facial expression to be recognized, and combining them to form a multiclass classifier, an average recognition rate of 79.4 % has been obtained for the 3D dynamic sequences showing the six prototypical facial expressions of the Bing- hamton University 4D Facial Expression database. Com- parisons with competitor approaches on the same database show that our solution is able to obtain effective results with the advantage of being capable to process facial sequences in real-time.