Print Email Facebook Twitter Optical flow-based facial feature tracking to recognize AUs modeled by Bayesian networks Title Optical flow-based facial feature tracking to recognize AUs modeled by Bayesian networks Author Sun, X. Contributor Wiggers, P. (mentor) Geers, H. (mentor) Braspenning, R. (mentor) Popa, M. (mentor) Rothkrantz, L.J.M. (mentor) Faculty Electrical Engineering, Mathematics and Computer Science Department Media Knowledge Engineering Date 2009-06-16 Abstract This thesis describes a Bayesian Network (BN) model for recognizing the “Action Units (AUs)” of a facial expression using video sequence images as input. Features were extracted by using an optimal estimation optical flow method coupled with a physical (muscle) model describing the facial structure. The muscle action patterns are used for analysis, recognition, and synthesis of facial expressions. In the thesis the main approaches to facial expression recognition of dynamic images are designed considering three main parts: 1) Region of Interest Selection, 2) Feature Extraction, and 3) Image Classification. Bayesian Networks are a powerful and flexible methodology for representing and computing with probabilistic models of a stochastic process. In the past decade, there has been increasing interest in applying them to practical problems, and this thesis shows that they can be used effectively in the field of automatic AU’s recognition. In past decade optical flows have been used to either model muscle activities or estimate the displacements of feature points but in this thesis we defined nine regions of interest (ROI) which contains the most complex motion by using entropy maximum algorithm. Furthermore, the results were statistically analyzed by compass diagrams to find out the major ranges of directions and velocities of vector flows in each ROI. We found that for the six basic emotions, the ROI are different, so we did not consider all of nine regions for every emotion because of the complexity of our model. Furthermore, we present a methodology for obtaining the BN structure, learning the parameters and inference, including issues such as the discretization of continuous variables. Finally, we apply the BN model to recognize single Action Units (AUs) and some important AU combinations. The average classification rate for the single AUs is between 80% and 90% and for the AU combinations is above 90% Subject Action Unit (AU)Bayesian Network (BN)emotion recognition To reference this document use: http://resolver.tudelft.nl/uuid:f1fdab34-07d6-455c-a4a6-1dc04b9f1196 Embargo date 2009-06-19 Part of collection Student theses Document type master thesis Rights (c) 2009 Sun, X. Files PDF thesis_xiaofan.pdf 5.65 MB Close viewer /islandora/object/uuid:f1fdab34-07d6-455c-a4a6-1dc04b9f1196/datastream/OBJ/view