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.
Automatic facial expression recognition in real-time from dynamic sequences of 3D face scans / Stefano Berretti; Alberto del Bimbo; Pietro Pala. - In: THE VISUAL COMPUTER. - ISSN 0178-2789. - STAMPA. - 29:(2013), pp. 1333-1350. [10.1007/s00371-013-0869-2]
Automatic facial expression recognition in real-time from dynamic sequences of 3D face scans
BERRETTI, STEFANO;DEL BIMBO, ALBERTO;PALA, PIETRO
2013
Abstract
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.File | Dimensione | Formato | |
---|---|---|---|
tvcj13.pdf
Accesso chiuso
Tipologia:
Versione finale referata (Postprint, Accepted manuscript)
Licenza:
DRM non definito
Dimensione
1.11 MB
Formato
Adobe PDF
|
1.11 MB | Adobe PDF | Richiedi una copia |
I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.