Facial Expression Analysis with Graphical Models

28353 Words114 Pages
Facial Expression Analysis with Graphical Models Lifeng Shang Department of Computer Science The University of Hong Kong A thesis submitted for the degree of Doctor of Philosophy Yet to be decided 2 Abstract of thesis entitled “Facial Expression Analysis with Graphical Models” Submitted by Lifeng Shang for the degree of Master of Philosophy at The University of Hong Kong in October 13, 2011 Facial expression recognition has become an active research topic in recent years due to its applications in human computer interfaces and data-driven animation. In this thesis, we focus on the problem of how to effectively use domain, temporal and categorical information of facial expressions to help computer understand human emotions. Over the past decades, many techniques (such as neural networks, Gaussian processes, support vector machines, etc.) have been applied to facial expression analysis. Recently, graphical models have emerged as a general framework for applying probabilistic models. They provide a natural framework for describing the generative process of facial expressions. In this thesis, we develop three different graphical models with different representational assumptions: categories being represented by prototypes, sets of exemplars and topics in between. Our first model incorporates exemplar-based representation into graphical models. It consists of three layers: observation layer, exemplars layer and prior knowledge layer. In the exemplars layer, exemplar-based model is integrated with graphical models to improve the accuracy of probability estimation with no assumption on prior distributions. In the prior knowledge layer, static graphical model is extended to temporal graphical model by considering historical observations to model temporal behaviors of facial expression. In the observation layer, facial features are traced
Open Document