本論文提出的演算法是針對簡單背景的灰階人臉影像,做自動化的表情辨識.在過去,利用人工類神經網路來做表情辨識有很好的成果.因此我們使用類似的方法來進行我們的辨識部分.我們的系統可以分成三個部分.第一部分為眼角偵測,眼角的位置及距離會當成參考值.第二部分為特徵擷取, 我們利用不同的描述方式來描述臉部特徵.此方法可以部分的減低因為光線或是雜訊所造成的誤差以達到較高的辨識成功率.最後就是我們使用Elman 類神經網路做辨識.,我們的實驗是使用JAFFE臉部資料庫做測試,辨識的表情共有七種,分別為中性,高興, 傷心, 厭惡, 生氣, 驚訝和恐懼.最後的結果顯示我們有八成的成功率.

　This Thesis aims at gray level facial images with simple background for automatic expression recognition. In the past, the neural network-based recognition methods are found to be particularly promising. We adopt a similar approach to efficiently recognize the facial expressions. Our system is divided into three phases. The first phase is canthi detection. The position of canthi is the reference object and the distance between canthi is the standard of judgment. The second phase is features extraction. We extract and describe the features from the contour of eyebrows, eyes and mouth by other ways. This method can reduce the partial influence of shadows and noises. Finally, We use the Elman Neural Network as our classifier. We use the JAFFE facial database to conduct our experiments. Our system recognizes seven basic types of human expressions – neutral, happy, sad, disgust, anger, surprise and fear. Simulation results demonstrate an expression classification accuracy of 80%.

[1] A. Mehrabian, "Communication without words," Psychol. Today, vol.2, pp. 53-56,1968.

[2] C.L. Huang and Y.M. Huang, "Facial Expression RecognitionUsing Model-Based Feature Extraction and Action ParametersClassification,"J. Visual Comm. and Image Representation, vol. 8,no. 3, pp. 278-290, 1997.

[3] H. Kobayashi and F. Hara, "Facial Interaction between Animated 3D Face Robot and Human Beings," Proc. Int'l Conf. Systems, Man, Cybernetics,, pp. 3,732-3,737, 1997.

[4] H. Hong, H. Neven, and C. von der Malsburg, "Online FacialExpression Recognition Based on Personalized Galleries," Proc.Int'l Conf. Automatic Face and Gesture Recognition, pp. 354-359, 1998.

[5] J. Steffens, E. Elagin, and H. Neven, "PersonSpotterDFast andRobust System for Human Detection, Tracking, and Recognition,"Proc. Int'l Conf. Automatic Face and Gesture Recognition, pp. 516-521,1998.

[6] M. Yoneyama, Y. Iwano, A. Ohtake, and K. Shirai, "FacialExpressions Recognition Using Discrete Hopfield Neural Networks," Proc. Int'l Conf. Information Processing, vol. 3, pp. 117-120,1997.

[7] M.J. Black and Y. Yacoob, "Recognizing Facial Expressions inImage Sequences Using Local Parameterized Models of ImageMotion," lnt'l J. Computer Vision, vol. 25, no. 1, pp. 23-48, 1997.

[8] M.J. Black and Y. Yacoob, "Tracking and Recognizing Rigid andNon-Rigid Facial Motions Using Local Parametric Models ofImage Motions," Proc. Int'l Conf. Computer Vision, pp. 374-381,1995.

[9] J. Zhao and G. Kearney, "Classifying Facial Emotions byBackpropagation Neural Networks with Fuzzy Inputs," Proc.Conf. Neural Information Processing, vol. 1, pp. 454-457, 1996.

[10] J.F. Cohn, A.J. Zlochower, J.J. Lien, and T. Kanade, "Feature-PointTracking by Optical Flow Discriminates Subtle Differences inFacial Expression," Proc. Int'l Conf. Automatic Face and GestureRecognition, pp. 396-401, 1998.

[11] B. Lucas and T. Kanade, "An Iterative Image Registration Technique with an Application to Stereo Vision," Proc. Joint Conf. Artificial Intelligence, pp. 674-680,1981.

[12] I. Essa and A. Pentland, "Coding, Analysis Interpretation,Recognition of Facial Expressions," IEEE Trans. Pattern Analysisand Machine Intelligence, vol. 19, no. 7,pp. 757-763, July 1997.

[13] M. Pantic and L.J.M. Rothkrantz, "Expert System for AutomaticAnalysis of Facial Expression," Image and Vision Computing J.,vol. 18, no. 11, pp. 881-905, 2000.

[14] Michael J.Lyons, Shigeru Akamatsu, Miyuki Kamachi & Jiro Gyoba,"Coding Facial Expressions with Gabor Wavelets,"Proceedings,Third IEEE International Conference on Automatic Face and Gesture Recognition,April 14-161998, Nara Japan, IEEE Computer Society, pp. 200-205.

[15] M.Lyons, J.Budynek, and S.Akamastu, "Automatic Classification of Single Facial Images", IEEE Trans. Pattern Analysis and Machine Intelligence, Vol.21, 1999, pp. 1357- 1362.

[16] Y.Shinohara and N.Otsu, "Facial Expression Recognition Using Fisher Weight Maps", IEEE Conf. on Automatic Face and Guesture Recognition, 2004, pp. 499-504.

[17] M.Gargesha and P.Kuchi, "Facial Expression Recognition using Artificial Neural Networks", EEE511: Artificial Neural Computation Systems, 2002.

[18] Xiaoyi Feng, "Facial Expression Recognition Based on Local Binary Patterns and Coarse-to-Fine Classification", The 4th International Conference on Computer and Information Technology, 2004, pp. 178-183.

[19] Y. Gao and M. K. H. Leung, "Human face recognition using line edge maps," in Proc. IEEE 2nd Workshop Automatic Identification Advanced Technologies, NJ, Oct. 1999, pp. 173-176.

[20] Ming-Wey Wu "Automatic Facial Expression Analysis System", the Thesis of Computer Science and Information Engineering, National Cheng Kung University, 2003.

[21] Fang-Sheng Su "Facial Expression Detection System" the Thesis of Communications Engineering, National Chung Cheng University,2004.