HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Conference papers

A face-to-muscle inversion of a biomechanical face model for audiovisual and motor control research

Michel Pitermann 1 Kevin G. Munhall
1 PAROLE - Analysis, perception and recognition of speech
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : Muscle-based models of the human face produce high quality animation but rely on recorded muscle activity signals or synthetic muscle signals often derived by trial and error. In this paper we present a dynamic inversion of a muscle-based model that permits the animation to be created from kinematic recordings of facial movements. Using a nonlinear optimizer (Powell's algorithm) the inversion produces a muscle activity set for 16 muscle groups in the lower face that minimize the root mean square error between kinematic data recorded with OPTOTRAK and the corresponding nodes of the modeled facial mesh. This inverted muscle activity is then used to animate the facial model. The results of a first experiment showed that the inversion-synthesis method can accurately reproduce a synthetic facial animation, even for a partial sampling of the face. The results of a second experiment showed that the method is as successful for OPTOTRAK recording of a talker uttering a sentence. The animation was of high quality.
Document type :
Conference papers
Complete list of metadata

Contributor : Publications Loria Connect in order to contact the contributor
Submitted on : Tuesday, September 26, 2006 - 2:47:28 PM
Last modification on : Wednesday, February 2, 2022 - 3:51:47 PM


  • HAL Id : inria-00100554, version 1



Michel Pitermann, Kevin G. Munhall. A face-to-muscle inversion of a biomechanical face model for audiovisual and motor control research. 7th European Conference on Speech Communication and Technology - EUROSPEECH'2001, ISCA, 2001, Aalborg, Denmark, 4 p. ⟨inria-00100554⟩



Record views