Facial Expression Classification using Kernel Principal Component Analysis and Support Vector Machines
John H. Ghent, Jane Reilly, John McDonald · Maynooth University ePrints and eTheses Archive (Maynooth University) · 2006
This paper details a novel procedure for accurately classifying lower facial expres- sions. A shape model is developed based on an anatomical analysis of facial expression called the Facial Action Coding System (FACS). This model analyzes the movement in shape due to the formation of a specific expression. We apply Kernel Principal Compo- nent Analysis (KPCA) to the shapes in the training set and classify new unseen expressions by using Support Vector Machines (SVMs). We further analyse our model by attaching a probability measure to the outputs.