Estimating muscle activation patterns using a surrogate model of facial biomechanics

Analyzing the muscle activities that drive the expressive facial gestures can be a useful tool in assessing one's emotional state of mind. Since the skin motion is much easier to measure in comparison to the actual electrical excitation signal of facial muscles, a biomechanical model of the human face driven by these muscles can be a useful tool in relating the geometric information to the muscle activity. However, long computational time often hinders its practicality. The objective of this study was to replace the precise but computationally demanding biomechanical model by a much faster multivariate meta-model (surrogate model), such that a significant speedup (real-time interactive speed) can be achieved and data from the biomechanical model can be practically exploited. Using the proposed surrogate, muscle activation patterns of six key facial expressions were estimated in the iterative fit from the structured-light scanned geometric information.

[1]  Paul D. Bolls,et al.  The Effects of Message Valence and Listener Arousal on Attention, Memory, and Facial Muscular Responses to Radio Advertisements , 2001, Commun. Res..

[2]  S. Wold,et al.  The multivariate calibration problem in chemistry solved by the PLS method , 1983 .

[3]  R. Manne.  Analysis of two partial-least-squares algorithms for multivariate calibration , 1987 .

[4]  Roman Rosipal,et al.  Overview and Recent Advances in Partial Least Squares , 2005, SLSFS.

[5]  S. Wold,et al.  Nonlinear PLS modeling , 1989 .

[6]  Veikko Surakka,et al.  Real-time estimation of emotional experiences from facial expressions , 2006, Interact. Comput..

[7]  M. Forina,et al.  Multivariate calibration. , 2007, Journal of chromatography. A.

[8]  L. Rubin.  The Mechanism of Human Facial Expression , 1992 .

[9]  C. Darwin.  The Expression of the Emotions in Man and Animals , .

[10]  N. P. Reddy,et al.  Facial expression (mood) recognition from facial images using committee neural networks , 2009, Biomedical engineering online.

[11]  Harald Martens,et al.  Screening design for computer experiments: metamodelling of a deterministic mathematical model of the mammalian circadian clock , 2010 .

[12]  Kostas Karpouzis,et al.  Emotion recognition through facial expression analysis based on a neurofuzzy network , 2005, Neural Networks.

[13]  Marko Grobelnik,et al.  Subspace, Latent Structure and Feature Selection techniques , 2006 .

[14]  Alistair A. Young,et al.  Cardiac Active Contraction Parameters Estimated from Magnetic Resonance Imaging , 2010, STACOM/CESC.

[15]  Peter J. Hunter,et al.  Simulating and Validating Facial Expressions using an Anatomically Accurate Biomechanical Model Derived from MRI Data - Towards Fast and Realistic Generation of Animated Characters , 2013, GRAPP/IVAPP.

[16]  H. Wold.  Path Models with Latent Variables: The NIPALS Approach , 1975 .

[17]  Harald Martens,et al.  Multi‐level binary replacement (MBR) design for computer experiments in high‐dimensional nonlinear systems , 2010 .

[18]  G. Boulogne,et al.  The Mechanism of Human Facial Expression , 1990 .

[19]  Regan L. Mandryk,et al.  A fuzzy physiological approach for continuously modeling emotion during interaction with play technologies , 2007, Int. J. Hum. Comput. Stud..

[20]  J. Brian Gray,et al.  Introduction to Linear Regression Analysis , 2002, Technometrics.

[21]  Falk Kiefer,et al.  The facial pattern of disgust, appetence, excited joy and relaxed joy: an improved facial EMG study. , 2005, Scandinavian journal of psychology.