Facial expressions are an important channel of non-verbal communication. An expression is a dynamic change of visual appearance involving the shape and position of facial features (the eyes, eyebrows, nose, and mouth), the coloration and condition of the skin and wrinkles. The main source that contributes to expression variation is facial muscular movements. We have used a registration framework, based on selected facial landmarks, to create expressions on surface models of the face. Deformation is applied to 3D face models with neutral expression to synthesize a corresponding model with some expression. Likewise when applied to 3D faces with expression the neutral expression can be synthesized. In addition to this work, we also analyse the optimal placement of landmarks to control facial expressions through deformation.
[1]
Alex Pentland,et al.
Coding, Analysis, Interpretation, and Recognition of Facial Expressions
,
1997,
IEEE Trans. Pattern Anal. Mach. Intell..
[2]
P. Ekman,et al.
Facial action coding system: a technique for the measurement of facial movement
,
1978
.
[3]
Takeo Kanade,et al.
Feature-point tracking by optical flow discriminates subtle differences in facial expression
,
1998,
Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.
[4]
Maja Pantic,et al.
Facial action recognition for facial expression analysis from static face images
,
2004,
IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).