3D動畫在多媒體世界中快速發展，其中，人體及虛擬人物的動作，表情更佔有舉足輕重的地位，不論在電玩、虛擬實境、以至於電影製作方面，如何製作一個逼真模型並使其產生各式各樣栩栩如生動作十分重要。目前提出建構3D人臉架構方法中，主要分成兩種不同類別：第一類為以電腦圖學技術為基礎，如幾何曲線多邊形和簡單幾何圖形。第二類為藉量測真實人臉方式進行，如雷射掃瞄，利用硬體直接取得；取得人臉表情動作方式，大致上包含有下面幾種：主要表情內差法(Keyframing)、Motion Capture及Simulation。本研究工作係利用兩個CCD攝影機同時左右拍攝標準人臉喜怒哀樂所呈現出臉部表情變化，將此兩個標準影像序列儲存後，於空間域中尋找特徵對應點，使用立體成像方法得到深度資訊以建構三度空間人臉模型；於時間域中進行特徵點比對，使用同一CCD攝影機連續前後兩張影像對應特徵點座標以推導特徵點位移向量，即可以得到二維人臉表情動作。每一特徵點經由空間域比對可得到三維資訊，並於時間域比對中推算每一特徵點運動向量結合三維資訊及運動向量即可建構一三度空間人臉模型之運動序列，於建立各種人臉表情之三度空間運動序列之前處理資料後，只要將其他人二度空間影像，與資料庫中標準人臉平面正照建立特徵點對應關係後，即可承襲資料庫中標準影像原特徵點深度與運動向量，將由標準影像得到3D資訊和位移向量資訊對應在其他平面正照上，使其成為三度空間模型，並模仿標準人臉動作，此一建立三維人臉模型運動序列資料庫，再將二維測試人臉影像對應至標準影像序列之方法對於日後建立人臉模型與模擬表情動作非常方便，其他測試影像平面只要與資料庫中標準影像正面建立特徵點對應後，即可承襲標準影像3D資訊和運動向量，過程中建立特徵點對應完全由電腦自行處理，不需人工經驗處理，非常節省人力。

3D animation has developed rapidly in the multimedia nowadays, in computer games, virtual reality and films. Therefore, how to make a 3D model which is really true to life, especially in the facial expressions, and can have vivid actions, is a significant issue. At the present time, the methods to construct 3D facial model are divided into two categories: one is based on computer graphic technology, like geometric function, polygon, or simple geometric shapes, the other one is using hardware to measure a real face by laser scanning system, and three-dimensional digitizer. Moreover, the method to acquire the 3D facial expression primarily are applied as following: keyframing, motion capture, and simulation.
The research covers two areas:
1. Use two CCDs to digitalize the facial expressions of a real person simultaneously from both right and left side, and save the obtained standard image. Then, get the feature match points from the two standard images in the space domain, and by using the Stereo to attain the “depth information” which helps to build 3D facial model.
2. Use one CCD to continuously digitalize two facial expressions and get the feature match points’ coordinates in the time domain to calculate the motion vector.
By combining the “depth information” from space domain and the motion vector from the time domain, the 3D facial model’s motion sequence can be therefore obtained.
If sufficient digitalized facial expressions are processed by the 3D facial model’s motion sequence, a database could be built. By matching the feature points between the 2D test image and 2D standard image in the database, the standard image’s “depth information” and motion vector can be used and turn the test image into 3D model which can also imitate the facial expressions of the standard images sequences. The method to match the feature points between the test image and standard images in the database can be entirely processed by computers, and as a result eliminate unnecessary human resources.

第一章 簡介
第一節 立體成像
第二節 2D和3D關係
第三節 比對技術
第二章 3D人臉模型建立與人臉動作模擬
第一節 3D人臉模型建立
一、 電腦圖學技術為基礎
二、 量測真實人臉方式進行
第二節 人臉動作模擬
第三章 研究方法步驟及結果
第一節 研究方法
第二節 步驟
一、 空間域比對建立3D模型
二、 時間域做Motion的比對
三、 測試影像2D 轉 3D
第四章 參考資料

[1] D.R. Forsey and R.H. Bartels, (1988)“Hierarchical B-spline fefinement”, In Computer Graphics(SIGGRAPH ’88) 22(4) , p:205-212。
[2] K. Waters and D. Terzopoulos, (1991)”Modeling and animating faces using scanned data”, J. of Visualization and Computer Animation, 2(4), p:123-128。
[3] T. Porter, (1983)“Spherical shading”, Computer Graphics(SIGGRAPH ’83) 17(3) , p:282-285。
[4] H.P. Moravec, (1977)”Towards automatic visual obstacle avoidance”, in Proc . 5th Int. Joint Conf. Artificial Intell., p:584。
[5] D. Marr and E. Hildreth, (1980) “Theory of edge detection”, Proc. Royal Soc.London vol B207, p:187-217。
[6] M. Peitikainen and D. Harwood, (1986) “Depth from three camera stereo”, in Proc. IEEE CS Conf. Pattern Recognition , p:2-8。
[7] N. Ayache and B. Faverjon, (1987)”Efficient registration of stereo images by matching graph descriptions of edge segments”, Int. J. Comput. Vision, p:107-131。
[8] Juyang Weng and Thomas W. Huang, (1992)”Matching Two Perspective View”, IEEE Transcations on pattern analysis and machine intelligence vol 14-8。
[9] D. Marr and T. Poggio, (1979)”A theory of human stereo vision”, in Proc. R. Soc. London vol B204, p:301-328。
[10] S. S. Sinha and B. G. Schunck, (1989)”Discontinuity preserving surface reconstruction”, in Proc. Conf. Comput. Vision Patt. Recogn, p:229-234. 。
[11] N. Magnenat-Thalmann, N.E. Primeau, and D. Thalmann., (1988) “Abstract muscle actions procedures for human face animation”, Visual Computer 3(5), p:90-297。
[12] T.W.Sendberg and S.R. Ladd, and K. Silverman., (1984)”Vocal cues to speaker affect: Testing two models”, Journal Acoustical Society of America, p:1346-1356。
[13] J. Chadwick, D. Haumann, and R. Parent, ( 1989) “Layered construction for deformable animated characters”, Computer Graphics 23(3), p:234-243。
[14] K. Waters, (1992)”A physical model of facial tissue and muscle articulation derived from computer tomography data”, In SPIE Conf. Visualization in Biomedical Computing Ineraction , p:574-583。
[15] Hai Tao, Thomas S.Huang, (1998)”Deriving Facial Articulartion Models From Image Sequences”, IEEE 0-81868821-1。
[16] Yuencheng Lee, Demetri Terzopoulos, and Keith Waters, (1995)”Realisitc Modeling for Facial Animation”, Computer Graphics Proceeding,Annual Conference Series。
[17] N. Magnenat-Thalmann, H. Minh, M. deAngelis, and D. Thalmann,(1988)”Design, transformation and animation of human faces”, The Visual Computer 5, p:32-39。
[18] Demetri Terzopoulos, (1993)”Analysis and Synthesis of Facial Image Sequence Using Physical and Anatomical Models”, IEEE Trans. On Pattern Analysis and Machine Intelligence 15.6, p:569-579。
[19] Watt, Policarpo, (1998)“The Computer Image “。
[20] A. Okabe, B.Boots, and K. Sugihara , (1995)“Spatial Tessellations”, Wiley, England.。
[21] A. M. Finch, R. C. Wilson, and E. R. Hancock, (1997)“Matching DELAUNAY Graphs,”, Pattern Recognition 30(1), p:123-140。.
[22] Y. Fisher, Ed., (1995)”Fractal Image Compression – Theory and Application”, New York: Springer-Verlag.。
[23] Xiaoming Liu,Yueting Zhuang, Yunhe Pan, (1999)”Video Based Human Animation Technique”, ACM 7th。
[24] J. Bloomenthal and B. Wyvill, (1993)”Interactive techniques for implicit modeling”,SIGGRAPH’93 。
[25] A.A. Ricci., (1973)”A constructive geometry for computer graphics”, The computer Journal 16(2), p:157-160。
[26]C.L. Waite Langwidere, (1993)”Hierarchical spline based facial animation system with simulated muscles”。.
[27]H. Gouraud,.(1971)”Continuous shading of curved surfaces”,.IEEE Trans on Computers 20(6), p:623-629。
[28]W.T Reeves, (1990)”Simple and complex facial animation,In State of the Art in Facial Animation”, SIGGRAPH’90 ACM, p:88-106。
[29]D. Terzopoulos, (1988)”The computation of visible-surface representations”, .IEEE Trans . on Pattern Analysis and Machine Intelligence, p:417-438。
[30]F. Glazer, G. Reynolds, and P. Anandan, (1983)”Scene matching by hieratchical correlation”, in Proc.IEEE Conf. Comput. Vision Patt. Recogn., p:432-441。
[31]H. S. Lim and T. O. Binford, (1987)”Stereo correspondence: A hierarchial approach”, in Proc. Image Understanding Workshop。
[32] Wolfgang Niem, (1999)”Automatic reconstruction of 3D objects using a mobile camera”, Image And Vision Computing Vol. 17 (2), p:125-134。
[33] R. Bowden, T.A. Mitchell and M. Sarhadi, (2000)”Non-linear statistical models for the 3D reconstruction of human pose and motion from monocular image sequences”, Image And Vision Computing Vol. 18 (9), p:729-737。
[34] E. Grossmann, and J. Santos-Victor, (2000)”Uncertainty analysis of 3D reconstruction from uncalibrated views”, Image And Vision Computin Vol. 18 (9) , p:685-696。
[35]H.P.Moravec, (1977)”Towards automatic visual obstacle avoidance”, in Proc. 5th Int. Ioint Conf. Artificial Intell., P.584。
[36]D. B. Gennery, (1980)”Object detection and measurement using stereo vision”, in Proc . ARPA Image Understanding Workshop, College Park, P:217-253。
[37]M. J. Hannah, (1980)”Bootstrap stereo”, in Proc. ARPA Image Understanding Workshop, College Park , p:201-208。
[38]F. I. Parke, (1982)”Parameterized model for facial animation”, IEEE Computer Graphics and Applications,2(9), p:61-68。
[39] F. I. Parke, (1990)”State of the Art in Facial animation”, SIGGRAPH ’90 Course Notes ACM 。
[40]W. T. Reeves, (1990)”Simple and complex facial animation: Case studies. In State of the Art in Facial Animation”, SIGGRAPH ’90 Course Notes ACM, p:88-106。
[41]Polhemus Navigations Sciences, (1987)”3Space Isotrack Users Manual”。