人臉是人類對於誰是誰的最基本判定方法, 但是電腦要像人類一樣分出誰是誰段目前而言仍然是項挑戰, 如何快速並準確的由連續的Video Stream中找到人臉, 並分析這個人是誰, 這取決於理論的正確選擇.
本文由一些不同的方向討論人臉辨識的理論, 實作, 實驗及結果, 這些方向分別是人臉的特性, 類神經網路, 及分析統計, 每個章節利用許多代表性的發表著作來討論其優缺點, 和其改善方法, 實驗的數據是利用Yale的人臉資料庫, 收集團體為 [C.V.C.], 資料庫包括15個人, 165張彩色影像, 每人十一張影像, 內容包含表情, 眼鏡, 與光線上的變化, 測試結果由Component數與錯誤率做比較.
由於區域特徵與廣與特徵對於人類五官或是整體的辨識率有某種程度影響, 所以文內舉出區域特徵的擷取辦法, 像是Local Feature Analysis與Local PCA, 做為討論, 而因為光線對於大多理論與方法都具有強烈的影響, 所以文內亦舉出由3-D Model面, 理論對光線適應面, 及影像修改面等三種大方向著手討論解決.

The human face is the basic way for human beings to recognize who a person is. Currently it is a challenge right now if we want the computer to recognize faces like humans do. How to detect and recognize faces in a video stream, quickly and accurately, depends on what algorithms you select and how you combine them.
In this paper we gather and compare algorithms, implementations, experiments, and results for face recognition from different sources. We compare three techniques: the constraint approach, artificial neural network approach, and statistic approach. We use lots of representative papers in each chapter to discuss their advantages, disadvantages, and how to improve them. The database we use is the Yale face database, which was created by the Computer Vision and Control (CVC) center at Yale Unversity. It includes 15 people, 11 images per person, for a total of 165 color images. The images in the database consist of various illumination conditions and facial expressions. The final test results are computed from their component numbers and error rate.
Local and global features have some influences for facial feature classification and recognition rate. Therefore we enumerate several local feature extraction algorithms, such as Local PCA and Local Feature Analysis and discuss how they work. Illumination conditions also affect recognition rate for most algorithms. We discuss the problem and try to solve it in three ways. The three ways are: 3-D model based, less sensitive algorithm based, and image modification based methods.

[1]B. Moghaddam,W. Wahid, and A. PentlandLinear, “Beyond Eigenfaces: Probabilistic Matching for Face Recognition” 3rd Face and Gesture, pages 30--35, 1998.
[2]B. Schölkopf, C. Burges, A. J. Smola “Advances in Kernel Methods - Support Vector Learning” MIT press. http://www.kernel-machines.org/nips97/book.html
[3]Baldi, P., Chauvin, Y., “Neural Networks for Fingerprint Recognition” Neural Computation, n. 5,1993, pp. 402-418.
[4]C. Lin, K. C. Fan, “Triangle-based approach to the detection of human face” Pattern Recognition 34 (2001) p1297-p1284
[5]C. Padgett and G. Cottrell, "Representing Face Images for Emotion Classification," Advances in Neural Information Processing Systems, MIT Press, 1997.
[6]Center for Computational Vision and Control “Yale Face Deatabase” http://cvc.yale.edu/projects/yalefaces/yalefaces.html , YaleUnversity
[7]Dowling, F. S. Roberts, P. Theuns, “Principal Component and Neural Network Analyses of Face Images: Explorations into the nature of information available for classifying faces by sex.” Mathematical psychology. Hillsdale: Erlbaum.
[8]D. Walsh, “Structure of Convolution Network.” http://wwwcs.sun.ac.za/courses/postgrad/hon/project_report/node23.htm 2000-02-12
[9]E. Hjelma , “Motion Detection”
[10]H. Rowley, S. Baluja, and T. Kanade “Neural Network-Based Face Detection” IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol. 20, No 1, January 1998.
[11]J. L. Crowley and F. Berard. “Multi-modal tracking of faces for video communication.” IEEE Conference on Computer Vision and Pattern Recognition, pages 640-645, 1997.
[12]Luiz-Marcos Garcia “Tracing Patterns and Attention: Humanoid Robot Cognition” Laboratory for Analysis and Architecture of Systems
[13]J. P. Kapur, “Face Detect in Color Image“, http://www.ece.cmu.edu/ jkapur/face.html
[14]J. Sobottka and I. Pitas. “Segmentation and tracking of faces in color images.” The Second International Conference on Automatic Face and Gesture Recognition, pages 236-241, 1996.
[15]J. T. Tou, R. C. Gonzalez, “Pattern Recognition Principles.” Addision Wesley Publishing Compony. 1974
[16]K. K. Sung, “Learning and Example Selection for Object and Pat-ternDetection,” PhD thesis, MIT AI Lab, Jan. 1996.
[17]Li-Fen Chen, “Person Identification Using Facial Information” Department of Computer Information Science College Conference.
[18]M. D. Garris, R. A. Wilkinson, and C. L. “Wilson Methods for Enhancing Neural Network Handwritten Character Recognition.” International Joint Conference on Neural Networks, Volume I IEEE, Seattle, July 1991.
[19]M. F. Augusteijn and T. L. Skujca. “Identification of human faces through texture-based feature recognition and neural network technology.” IEEE Conference on Neural Networks, page 392-398, 1993.
[20]M. H. Yang and D. Kriegman. “Detecting Face in Images: A Survey.” IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2001.
[21]M. J. Lyons, J. Budynek, S. Akamatsu, “Classifying Images of Facial Expression using a Gabor Wavelet Representation” Proceedings, 2nd International Conference on Cognitive Science, Waseda University, Tokyo, Japan, 27-30 July 1999, pp. 113-118.
[22]P. Juell and R. Marsh. “A hierarchical neural network for human face detection.” IEEE Conference on Computer vision and Pattern Recognition, volume 1, pages 274-280, 1999.
[23]P. N. Belhumeur J. P. Hespanha D. J. Kriegman “Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection.” IEEE Trans. on PAMI, July 1997.
[24]P.S. Penev and J.J. Atick, "Local Feature Analysis: A General Statistical Theory for Object Representation.” Network: Computation in Neural Systems, vol. 7, no. 3, pp. 477-500, 1996.
[25]R. Feraud "PCA, Neural Networks and Estimation for Face Detection", The NATO Advanced Study Institute to Applications, Stirling, Scotland, UK, 1997
[26]S. Gong, “Location and Tracing Face using colour”
[27]R. Ismaeil, A. Docef, F. Kossentini, and R. Ward “Motion Estimation Using Long Term Motion Vector Prediction.” University of British Columbia.
[28]R. Kjeldsen and J. Kende. “Finding skin in color image.” The Second International Conference on Automatic Face and Gesture Recognition, pages 312-317, 1996.
[29]R. O. Duda, P. E. Hart, “Pattern Classification And Scene Analysis” Wiley, New York.P.130-134
[30]S. Georphiades, P. N. Belhumeur, D. J. Kriegman. “From Few to Many: Illumination Cone Model for face Recognition Under Variable Lighting and Pose” IEEE Trans. Pattern Analysis and Machine Intelligent.
[31]S. Lawrence, C. L. Giles, A. C. Tsoi, “A Convolutional Neural Network Approach.” IEEE Transactions on Neural Networks, Special Issue on Neural Networks and Pattern Recognition, olume 8, Number 1, p98—113, 1997.
[32]S. Mukherjee and V. Vapnik “Multivariate Density Estimation: a Support Vector Machine Approach” A.I. Memo No. 1653 April 1999 C.B.C.L Paper No. 170”
[33]S. Romdhani, “Face Recognition Using Principal Component Analysis”, http://www.elec.gla.uk/~romdhani/pca.htm
[34]T. M. Mitchell. “Machine Learning” The McGraw-Hill Companies, Inc.
[35]Valentin, D., Abdi, H., O''Toole, A.J. (in press). “Principal component and neural network analyses of face images: Explorations into the nature of information available for classifying faces by sex.” In C. Dowling, F.S. Roberts, P. Theuns, Progress in Mathematical Psychology.
[36]V. Krüger, G. Sommer “Gabor Wavelet Network for Object Representation” Dagstuhl Workshop on Theoretical Foundations of Computer Vision.
[37]W. Zhao, A. Krishnaswamy, R. Chellappa, D. L. Swets, J. Weng “Discriminant Analysis of Principal Components for Face Recognition” Springer-Verlag, pp. 73-85, 1998.
[38]Y. Cheng, K. Liu, J. Yang, Y. Zhuang, and N. Gu, “Human Face Recognition Method Based on the Statistical Model of Small Sam-ple Size,” SPIE Proc. Intelligent Robots and Computer Vision X: Algo-rithms and Technology, 1991, pp. 85-95.
[39]Y. LeCun, Y. Bengio, “Convolutional Networks for Images, Speech, and Time-Series” The Handbook of Brain Theory and Neural Network. P.255-p.258 MIT Press.
[40]Y. Moses, Y. Adini, and S. Ullman, “Face Recognition: The Prob-lem of Compensating for Changes in Illumination Direction,” European Conf. Computer Vision, 1994, pp. 286-296.