Facial expression recognition system based on a face statistical model and Support Vector Machines

摘要

Facial expression recognition is an important research domain in developing human-machine relations. This paper proposes a facial expression recognition system. This system is built using Constrained Local Models to fit the shapes on a face image and on Support Vector Machines (SVMs) to detect the face expressions. Different SVM architectures and trainings have been used including applying outliers filtering to obtain better recognition rates.