臺灣博碩士論文加值系統

在本篇論文中，我們應用臉部特徵點的技術，發展出臉部表情變化的合成以及臉部辨識系統。由於特徵點代表著每張臉孔五官位置的特徵，因此我們將之運用於臉部辨識系統上。本篇論文中，我們提出了一種自動偵測及辨識人臉的方法。依照膚色色度分布集中的特性，可以偵測出影像中人臉的位置。接著經過影像處理後，找出所偵測到的臉孔特徵點的座標，利用這些特徵點座標，即能求出代表整張臉部的特徵向量。當系統進行辨識時，僅需比對特徵向量間的差異值，即可判斷出身分。本系統在速度方面及辨識率上都能得到相當良好的效果，在論文後面我們將列舉出本系統的實驗結果。
另外，近年來由於MPEG-4標準的發展，臉部表情變化合成技術逐漸受到重視。一般最常被使用的技術是利用網狀模型來合成臉部表情。在這裡我們利用了所謂的Elastic body spline (EBS)之方法，合成二維的臉部表情之影像。Elastic body spline是一套以物理特性為基礎的座標轉換系統，可以對原始臉部模型產生適當的形變，合成出逼真的有表情臉。由於EBS轉換系統是利用有限的特徵點，以及物體的物理特性參數來完成。因此，在本篇論文中，我們提出了一種遞迴演算法，在假設同一區域的特徵點與非特徵點有相同的物理特性下，找出臉部不同區域各自的物理特性參數。利用這些參數，即可獲得經過EBS轉換後所有點的座標，合成出有表情變化的臉。

In this thesis, we developed a facial expressional model synthesis and recognition system based on feature point techniques. Feature point identifies exact positions of human facial features, therefore they are applicable for face recognition systems. We proposed an automatic detection and recognition scheme based on the property that the skin colors are distributed over a small area in the chrominance plane to detect human face positions. Furthermore, we can successfully extract the coordinates of feature points via image processing techniques. By using these coordinates, feature vectors of faces can be derive. System can use differences of feature vectors between distinct face models for performing identification task. Experimental results based on this scheme will be presented in later chapters.
Besides, due to the advent of MPEG-4 standard, facial animation receives significant attentions recently. A common approach for facial animation is to use the mesh model. The physics-based transformation, elastic body spline (EBS), has been proposed to deform the facial model and generate realistic expression successfully. However, the EBS transformation is based on some limited feature points and the physical properties of the object. In this paper, we propose an iterative algorithm to find the EBS for non-feature points by assuming that the elastic bodies for feature and non-feature points have the same physical properties in a region. By doing so, we can obtain the EBS for every mesh vertices such that facial animation can be more realistically achieved.

Chapter 1 Introduction.........................................1
1.1 Face Recognition..........................................1
1.2 Facial Expressions........................................3
Chapter 2 Face Recognition System..............................5
2.1 Face Location.............................................7
2.1.1 Convert RGB format to YCbCr.............................8
2.1.2 Skin color classifier..................................10
2.1.3 Removing the isolated pixels...........................14
2.1.4 Select face region.....................................15
2.2 Eyeballs Location........................................16
2.2.1 Binarize image.........................................17
2.2.2 Correlation............................................18
2.3 Rotate image on the z-axis...............................19
2.4 Binarizing image.........................................20
2.5 Feature Points Extraction................................23
2.6 Rotate image on the y-axis...............................26
2.7 Feature Vectors..........................................31
2.7.1 Vectors................................................31
2.7.2 Length of vector.......................................33
2.8 Compare with database....................................34
2.8.1 Euclidean Distance.....................................34
2.8.2 Hamming Distance.......................................35
Chapter 3 Facial Expression .................................37
3.1 Principle of Elastic Body Spline transformation..........37
3.2 System Algorithm.........................................40
3.2.1 Create original facial model...........................43
3.2.2 Facial region selection................................43
3.2.3 2D Inverse Elastic Body Spline transform system........44
3.2.4 2D Elastic Body Spline transform system................45
3.2.5 Iterative algorithm for finding Poisson’s ratio of each region.......................................................47
Chapter 4 Experimental Results...............................50
4.1 Face Recognition.........................................50
4.1.1 Euclidean Distance.....................................52
4.1.2 Hamming Distance.......................................56
4.1.3 Size of Face...........................................59
4.2 Facial Expression........................................61
Chapter 5 Conclusion.........................................64
References...................................................66

[1] Chellappa, R.; Wilson, C.L.; Sirohey, S. “Human and machine recognition of faces: a survey,” Proceedings of the IEEE, vol. 83, pp. 705-741, May 1995
[2] Hualu Wang; Shih-Fu Chang, “A highly efficient system for automatic face region detection in MPEG video,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 7, no. 4, pp. 615-628, Aug. 1997
[3] Chai, D.; Ngan, K.N. “Automatic face location for videophone images,” 1996 IEEE TENCON- Digital Signal Processing Applications, vol. 1, pp. 137-140, 1996
[4] Brunelli, R.; Poggio, T. “Face recognition: features versus template,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, no. 10, pp. 1042-1052, Oct. 1993
[5] Turk, M.A.; Pentland, A.P. “Face recognition using eigenfaces,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 586-591, 1991
[6] Garcia, C.; Tziritas, G. “Face detection using quantized skin color regions merging and wavelet packet analysis,” IEEE Transactions on Multimedia, vol. 1, no. 3, pp. 264-277, Sept. 1999
[7] Son Lam Phung; Chai, D.; Bouzerdoum, A. “A universal and robust human skin color model using neural networks,” International Joint Conference on Neural Networks, vol. 4, pp. 2844 —2849, 2001
[8] Chai, D.; Ngan, K.N. “Face segmentation using skin-color map in videophone applications,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 9, no. 4, pp. 551-564, Jun. 1999
[9] Bojic N.; Pang K. K. “Adaptive skin segmentation for head and shoulder video sequence,” Visual Communication and Image Processing 2000, vol. 4067, pp. 704-711, Jun. 2000
[10] Menser B.; Wien M. “Segmentation and tracking of facial regions in color image sequences,” Visual Communication and Image Processing 2000, vol. 4067, pp. 731-740, Jun. 2000
[11] Jiang, X.; Binkert, M.; Achermann, B.; Bunke, H. “Towards detection of glasses in facial images,” Fourteenth International Conference on Pattern Recognition, vol. 2, pp. 1071-1073, 1998
[12] Kothari, R.; Mitchell, J.L. “Detection of eye locations in unconstrained visual images,” International Conference on Image Processing, vol. 3, pp. 519-522, 1996
[13] Jian Huang Lai; Yuen, P.C.; Wen Sheng Chen; Lao, S.; Kawade, M. “Robust facial feature point detection under nonlinear illuminations,” IEEE ICCV Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems, pp. 168-174, 2001
[14] 黃瑞松, “Constructing 3D Facial Models for Next Generation Video Coding,” 國立中正大學電機工程研究所碩士論文, pp. 42-43, 1998
[15] Kin-Man Lam; Hong Yan, “An analytic-to-holistic approach for face recognition based on a single frontal view,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20, no. 7, pp.673-686, 1998
[16] Nefian, A.V.; Hayes, M.H., III, “Hidden Markov models for face recognition,” IEEE International Conference on Acoustics, Speech and Signal Processing, vol. 5, pp.2721-2724, 1998
[17] Phiasai, T.; Arunrungrusmi, S.; Chamnongthai, K. “Face recognition system with PCA and moment invariant method,” ISCAS 2001, vol. 2, pp. 165-168, 2001
[18] Ki-Chung Chung; Seok Cheol Kee; Sang Ryong Kim, “Face recognition using principal component analysis of Gabor filter responses,” International Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems, pp. 53-57, 1999
[19] Vinayadatt V. K.; Desai U. B. ”Face recognition,” IEEE International Symposium on Circuits and Systems 2000, pp. 305-308, 2000
[20] Goudail, F.; Lange, E.; Iwamoto, T.; Kyuma, K.; Otsu, N. “Face recognition system using local autocorrelations and multiscale integration,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 18, no. 10, pp. 1024-1028, Oct. 1996
[21] Menser, B.; Muller, F. “Face detection in color images using principal components analysis,” Seventh International Conference on Image Processing and Its Applications, vol. 2, pp. 620-624, 1999
[22] Jeonghee Park; Jungwon Seo; Dongun An; Seongjong Chung “Detection of human faces using skin color and eyes,” ICME 2000, vol. 1, pp. 133-136, 2000
[23] Zhong Jing; Robert Mariani “Glasses detection and extraction by deformable contour,” 15th International Conference on Pattern Recognition, vol. 2, pp.933-936, 2000
[24] Byeong Hwan Jeon; Sang Uk Lee; Kyung Mu Lee, “Rotation invariant face detection using a model-based clustering algorithm,” ICME 2000, vol. 2, pp. 1149-1152, 2000
[25] Li, S.Z.; Juwei Lu, “Face recognition using the nearest feature line method,” IEEE Transactions on Neural Networks, vol. 10, no. 2, pp.439-443, 1999
[26] 蔡孟翰, “使用彈性物體轉換完成之臉部表情合成系統研究,” 國立中正大學電機工程研究所碩士論文, 2000
[27] John W. Hole, Karen A. Koos, Human Anatomy, 1992
[28] I. S. Sokolnikoff, Mathematical Theory of Elasticity, McGraw-Hill, New York, 1956
[29] S. Timoshenko and J. N. Goodier, Theory of Elasticity, McGraw-Hill, New York, 1951
[30] Kuo, C.J.; Ruey-Song Huang; Tsang-Gang Lin, “3-D facial model estimation from single front-view facial image,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 12, no. 3, pp. 183-192, 2002
[31] “MPEG-4 Committee Draft,” Coding of moving pictures and audio, ISO/IEC/JTC1/SC29/WG11 N2196, Mar. 1998
[32] Ciarlet, Philippe G, Mathematical elasticity. North-Holland, 1988