由於近年來人臉辨識已經廣泛被研究，而許多辨識的方法與理論也隨之而產生，但往往大部分的人臉辨識在人臉的角度上有著嚴格的限制，在本論文當中提供了虛擬的人臉系統以供多角度的辨識，只需一張正面的人臉，便可虛擬出不同角度的人臉，同時為了克服單張影像欠缺深度資訊的問題，所以加入了一般統計的方法去判斷臉型大概的深度，以減少在虛擬時誤差的產生，此識別系統主要包含人臉偵測、人臉虛擬以及人臉辨識三個系統。
人臉偵測系統中，利用膚色找到人臉的搜尋區域後，依橢圓樣板演算法，找出人臉的影像，再取得人臉上面各個特徵點資訊，進而模擬出三維的人臉，在擷取各角度的圖形做為判斷人臉的虛擬資料庫，最後以主分量分析（Principal Component Analysis，PCA）確認偵測到的影像是否為資料庫人臉影像。簡言之，本論文前段虛擬人臉系統可與其他的人臉辨識系統結合，並使判斷角度上有更大的彈性。

Face recognition system has been widely developed in recent years. Many methods and theories of recognition also have been created. However, most of face recognition systems involve strict constraints on angles of human faces. In this thesis, it will present a simulation system to provide face recognition from various angles. The system only requires the front side of a face and then , further , to simulate various angles of the face. Moreover, in order to overcome the issue that a single image lacks deeply detailed information, this system will apply statistic method to identify the approximate depth of the face to decrease the occurrence of deviation when simulating. The recognition system mainly includes face testing system, face simulation system and face recognition system.

In face testing system, it will utilize skin tone to find out the search area of faces. By ellipsoidal mask, images of faces can be identified and information of every characteristic can be obtained, further to simulate three-dimensional faces. These images with various angles can be captured to be used as a simulation database for face recognition. Finally, the system ensures whether the obtained images are face images in database by Principal Component Analysis technique. Briefly, this thesis will describe that the face simulation can be combined with other face recognition systems and achieve to higher elasticity in identifying angles.

[1]. L. Wiskott, Jean M. Fellous And Christoph V. D. Malsburg, “Face recognition
by elastic bunch graph matching,” IEEE Transactions on Pattern Analysis and
Machine Intelligence, Vol. 19, No. 7, pp. 775-779, 1997.

[2]. T. Vetter and T. Poggio, “Linear object classes and image synthesis from a single
example image,” IEEE Transactions on Pattern Analysis and Machine Intelligence,
Vol. 19, No. 7, pp. 733-742, 1997.

[3]. C.Garcia and G.tzirita, “Face detection using quantized skin color region merging and wavelet packet analysis “, IEEE trans . Multimedia , pp.264-277 ,1999.

[4]. C.Garcia,G.simandiris and G.tzirita ,“A feature-based face detector using wavelet
frames”,Proc. of Int. , Workshop on very low bit coding , pp . 71-76 , 2001.

[5]. A.Pentland,B.Moghaddam and T.Starner , ” View-based and modular eigenspaces for face recognition ” , Proc. IEEE Conf. Computer Vision and Pattern Recognition , pp.
84-91,1994.

[6]. E.Osuna,R.Freund and F.Girosi, “ Training support vector machines : an application to
face detection “ , Proc. IEEE Conf. Computer Vision and Pattern Recognition ,
pp. 130-136,1997.

[7]. R.Brunelli and T.Poggio , “ Face recognition : features vs.template” , IEEE Trans.
Pattern Analysis and Machine Intelligence, Vol.15 ,No. 10,pp. 1042-1052, 1993

[8]. Quan YUAN, Wen GAO and Hongxun YAO,” Robust frontal face detection in complex environment “, Pattern Recognition, 2002. Proc. 16th International Conference on , Vol.1 , pp. 25-28 , Aug. 2002.

[9]. Garcia and G.tzirita, “Face detection using quantized skin color region merging and wavelet packet analysis “, IEEE Transactions. Multimedia , 1(3):264-277 ,1999.

[10]. R.Feraud, O.J.Bernier ,J.E.Viallet, and M.collobert, “ A fast and accurate face detection based on neural network” , IEEE Trans. Pattern Analysis and Machine Intelligence,Vol.23 , No.1 , pp.42-53, Jan, 2001.

[11]. H.Wu , Q.Chen, M.Yachida ,” Face detection from color using a fuzzy Pattern match method “ , IEEE Trans. Pattern Analysis and Machine Intelligence, Vol.21 , No.6 ,pp.557-563, June, 1999.

[12]. K. Bowyer, K. Chang, and P. Flynn, “A survey of approaches and challenges in 3D and multi-Modal 3D 2D face recognition,” IEEE Transactions on Computer Vision and Image Understanding, Vol. 101, No. 1, pp. 1-15, 2006.

[13]. K.I. Chang, K.W. Bowyer, and P.J. Flynn, “Multiple nose region matching for 3d face recognition under varying facial expression,”IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 28, No. 6, pp. 1695–1700, October 2006.

[14]. K.W. Bowyer, K.I. Chang, and P.J. Flynn, “A survey of approaches and challenges in 3d and multi-modal 3d+2d face recognition,” Computer Vision and Image Understanding, Vol.101, No. 1, pp. 1–15, January 2006.

[15]. M. Turk and A. Pentland, “Eigenfaces for recognition,” Jour. Of Cognitive Neuroscience, Vol. 3, pp.71-86, 1991.

[16]. L. Sirovich and M. Kirby, “Low-dimensional procedure for the characterization of human faces,” J. Opt. Soc. Amer.4, pp.519-524, 1987.

[17]. Hua Yu, Jie Yang, “A Direct lda algorithm for high dimensional data with application to face recognition”, Pattern Recognition, pp.2067-2070,Vol.34, 2001

[18]. H. Yu and J. Yang, “A Direct IDA Algorithm for High Dimensonal Data with Application to Sace Recognition,＂Pattern Recognition, Vol. 34, pp. 2067-2070, 2001

[19]. C. Wong, D. Kortenkamp, and M. Speich, “A Mobile Robot that Recognizes People,＂IEEE Int. Conf. on Tools with Artificial Intelligence, 1995.

[20]. R. C. Gonzalez and R. E. Woods 著，數位影像處理，繆紹綱譯，台灣培生教育出版，台北，民國九十三年。

[21]. C. Garcia, and G.Tziritas. “ Face Detection Using Quantized Skin Color Regions Merging and Wavelet Packet Analysis.” in IEEE Transactions on Multimedia Vol. 1 , No. 3 , pp. 264-277, 1999.

[22]. A. McAndrew 著，數位影像處理，徐曉珮譯，新加坡商湯姆生亞洲私人有限公司台灣分公司，台北，民國九十四年。

[23]. L. G. Shapiro and G. C. Stockman, “Computer Vision,” pp.65-68, Prentice-Hall, NJ, 2001.

[24]. S. Birchfield, “An Elliptical Head Tracker,” Conf. Record of the asilomar Conf. on Signals, Systems & Computers, Vol.2, pp.1710-1714,November 1997.

[25]. S. Birchfield, “Elliptical Head Tracking Using Intensity Gradients and Color Histograms,” Proc. of the IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, pp.232-237, June 1998.

[26].冬陽 著，3D遊戲程式設計/基礎篇，寰宇出版社，台北，民國九十二年。

[27].楊宜學，頭部尺寸測量方法與結果，行政院勞委會計畫，計畫編號：IOSH-H222
，1997