Instalment of a facial expression is associated with contractions and 6 extensions of specific facial muscles. Noting that expression is about changes, we 7 present a model for expression classification based on facial landmarks dynamics. Our 8 model isolates the trajectory of facial fiducial points, by wrapping them up in relevant 9 features and discriminating among various alternatives with a machine learning 10 classification system. The used features are geometric and temporal based and the

more »

... 11 classification system is represented by a late fusion framework that combines several 12 neural networks with binary responses. The proposed method is robust, being able to 13 handle complex expression classes. 14