在這篇論文裡，我們提出了兩個圖形模組來針對自動偵測人臉特徵以及計算人臉影像上用來萃取出表情特徵的光流場變化。為了解決這樣的問題，我們應用了在圖形模組上常用的信念傳遞演算法 (LBP) 架構。在第一部份，我們學習每個特徵的主要分量分析模組 (PCA) 和幾何上的關係以用來建構人臉特徵的圖形模組。在第二部份，我們對光流場計算來建構一個馬可夫亂數場模組 (MRF)；這個模組架構的目的是用來確定在無表情影像中的一小片影像可以對應到有表情影像中正確的對應位置。加上區域性特徵限制可以使得在特徵位置上的光流場更加精確。最後，我們可以結合這兩個演算法和支援向量機 (SVM) 的分類器來開發一個表情辨識系統。

In this thesis, we propose two graphical models for automatically detecting facial features and estimating optical flow on face images for extracting the expression flow features. To accomplish these tasks, we apply the Loopy Belief Propagation (LBP) algorithm which is a common framework for graphical model. In the first part, we learn the feature PCA models and geometry relationship for building a graphical model for facial features. In the second part, we build a Markov Random Field (MRF) model for optical flow estimation, and the purpose of the model structure is to make sure that the patch of neutral image could move to correct corresponding position on the expression image. The local feature constraint makes the optical flow computation in the feature areas more precise. Finally, we combine these two algorithms with the SVM classifier to develop a facial expression recognition system.

[1] Y. Yacoob and L.S. Davis, “Recognizing Human Facial Expressions from Long Image Sequences Using Optical Flow,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, no. 6, pp. 636-642, 1996.
[2] Lanitis, A., Taylor, C.J., and Cootes, T. F., “Automatic Interpretation and Coding of Face Images Using Flexible Models,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 743-756. , 1997.
[3] Yongmian Zhang and Qiang Ji, “Active and Dynamic Information Fusion for Facial Expression Understanding from Image Sequences,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, no. 5, 2005
[4] Michael I. Jordan. “Learning in Graphical Model,” MIT Press, 1999.
[5] Kevin P. Murphy. “An introduction to graphical models,” May 2001
[6] W. T. Freeman and E. C. Pasztor. “Markov networks for super-resolution.” In Proc. 34th Annual Conf. on Information Sciences and Systems (CISS 2000), 2000.
[7] Pearl, Judea. “Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference (2nd edition).” San Francisco: Morgan Kaufmann Publishers, Inc, 1988.
[8] K. P. Murphy, Y. Weiss, and M. I. Jordan. “Loopy belief propagation for approximate inference: an empirical study.” In Proc. of UAI, pp. 467-475, 1999.
[9] Jian Sun, Heung-Yeung Shum, and Nan-Ning Zheng. “Stereo matching using belief propagation.” ECCV, 2002.
[10] Pedro F. Felzenszwalb and Daniel P. Huttenlocher. “Efficient Belief Propagation for Early Vision,” IEEE CVPR, vol. 1, pp. 261-268, 2004.
[11] Rein-Lien Hsu, Mohamed Abdel-Mottaleb, and Anil K. Jain. “Face detection in color images.” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002.
[12] S. Osher L.I. Rudin and E. Fatemi. “Nonlinear total variation based noise removal algorithm.” Physica D, 27(60)：259-268, 1992
[13] P.N.Belhumeur, J.P.Hespanha and D.J.Kriegman. “Eigenfaces vs Fisherfaces: recognition using class specific linear projection”. TPAMI, vol.20, no.7, 1997.
[14] Xiaozhou Wei; Yi Sun; Jun Wang; Matthew J. Rosato, ”A 3D Facial Expression Database For Facial Behavior Research” by Lijun Yin; 7th International Conference on Automatic Face and Gesture Recognition (FGR06), 10-12 April 2006 P:211 - 216