臺灣博碩士論文加值系統

在過去二十年裡，生物認證於安全維護方面被逐漸廣泛應用。尤其，以人臉為特徵而進行辨識，在生物認證領域裡，更是被積極研究著。本研究之主要目的為建構一套有效之人臉辨識系統，於特徵擷取方法上，採主成份分析(Principal Component Analysis, PCA)及區域自相關係數(Local Autocorrelation Coefficient, LAC)等兩種特徵擷取方法，並將此兩種特徵擷取方法進行整合，利用兩特徵擷取方法整合後，便會增加影像之特徵數，以提高人臉辨識結果。並利用二維影像之資訊加上三維影像之資訊，即加入影像之深度資訊，以突破僅採用二維影像之平面資訊，於辨識之瓶頸。最後於分類方法上，採用倒傳遞類神經網路(Back-Propagation Neural Network, BP)與歐氏距離(Euclidean Distance)等兩種分類方法，期能發展出一套有效之人臉辨識系統。本研究共對一百位受測者進行取像，每位受測者均取十三種不同之表情影像，實驗中，以表情一至表情七作為訓練影像，表情八至表情十三為測試影像，由實驗結果得知，將二維影像及三維影像之資訊進行整合，對辨識結果均能有效提昇；而PCA與區域自相關係數兩特徵擷取方法之結合，於歐氏距離上，對辨識結果並不能有效提昇，亦有可能造成反效果；但若改以倒傳遞類神經網路進行分類，對辨識率之提昇即有所助益；最後，將歐氏距離與倒傳遞類神經網路等兩分類方法相比較，得知倒傳遞類神經網路之分類效果優於歐氏距離之分類效果。

Biometric measurements received an increasing interest for security applications in the last two decades. In particularly, face recognition has been an active research in this area. The objective of this study is to develop an effective face recognition system that extracts both 2D and 3D face features to improve the recognition performance. The proposed method derives 3D face information using a designed stereo face system. Then, it retrieves 2D and 3D face features with Principle Component Analysis (PCA) and Local Autocorrelation Coefficient (LAC) respectively. Eventually, the information of features are fused and fed into a Euclidean-distance classifier and a Backpropagation neural network for recognition.
An experiment was conducted with 100 subjects. For each subject, thirteen stereo face images were taken with different expressions. Among them, the faces with expressions one to seven are used for training, and the rest of the expressions is used for testing. For the Euclidean-distance classifier, the proposed method does not improve the recognition result by combining the features derived from PCA with LAC; however, an improvement is observed when using the Back-Propagation Neural Network. In general, BP outperforms Euclidean distance in both 2D and 3D face recognition. Furthermore, the experimental results show that the proposed method effectively improves the recognition rate by combines the 2D with 3D face information.

中文摘要I
ABSTRACTIII
目錄VI
表目錄VIII
圖目錄IX
第一章 緒論1
1-1 研究背景與動機 1
1-2 研究目的2
1-3 研究範圍與限制 3
1-4 研究架構4
第二章 文獻探討5
2-1 人臉辨識之文獻探討5
2-2 主成份分析法7
2-3 區域自相關係數理論9
2-4 倒傳遞類神經網路10
2-5 雙影像簡介15
2-5-1 雙影像原理16
2-5-2 雙影像對應之相關研究17
2-5-3 雙影像對應法之分類18
2-6 三維人臉之辨識 21
2-6-1雷射掃瞄系統(Laser Scan System) 21
2-6-2 使用物體照度變化程度計算深度 (Shape From Shading, SFS)23
2-6-3 使用雙影像視覺方式（Stereo Vision）25
2-6-4 使用三維資訊之人臉辨識系統比較27
第三章 研究方法32
3-1 系統架構32
3-2 雙影像對應38
3-3 主成份分析40
3-4 區域自相關係數 44
3-5 倒傳遞類神經網路47
第四章 實驗結果與分析51
4-1 實驗環境51
4-2 實驗樣本及取像 52
4-3 實驗參數設定56
4-4 實驗結果及分析70
第五章 結論及後續研究建議76
5-1 結論76
5-2 研究貢獻77
5-3 後續研究建議77
參考文獻79
附錄一88
附錄二90

參考書籍
[1] 林清山，變項分析統計法，台北市 ： 東華圖書有限公司，1988
[2] 繆紹綱譯，數位影像處理，台北市：高立圖書有限公司，2003。
[3] 吳成柯；程湘君；戴善榮；雲立實，數位影像處理，台北市：儒林圖書有限公司， 2001。
[4] 葉怡成，類神經網路模式應用與實作，台北市：儒林圖書有限公司， 2002。
[5] 葉怡成，應用類神經網路，台北市：儒林圖書有限公司， 1997。
[6] Shirai, Y. , Three-Dimensional Computer Vision, New York: Springer-Verlag,1987.
[7] Touretzky, S., and Lipmann, R., San Mateo, Eds., CA: Morgan Kaufmann, San Fransisco:Morgan Kaufmann Publishers Inc., 1999, pp.572-577.

期刊論文
[8]Ackermann, F., “Digital image correlation-performance and potential application in photogrammetry,” Photogrammetric Record, Vol. 11, No.64, 1984, pp. 429-439.
[9] Akamatsus, S., Sasaki, T., fukamachi, H, and Suenaga, Y., “A robust face identification scheme-KL expansion of an invariant feature space,“ in SPIE Proc. : Intell. Robots and Computer Vision X: Algorithms and Techn, vol. 1607, 1991, pp.71-84.
[10] Bartlett, M.S., Movellan, J.R., and Sejnowski, T.J., “Face Recognition by Independent Component Analysis,” IEEE Trans. Neural Networks, vol. 13, no. 6, 2002, pp.1450-1464.
[11] Brunelli, R. and Poggio, T., “HyperBF networks for gender classification,“ in Proc., DARPA Image Understanding Workshop, 1992, pp. 311-314.
[12] Calitz, M.-F., and Ruether, H.,”Least absolute deviation (LAD) image matching,” ISPRS Journal of Photogrammetry and Remote Sensing ,Vol. 52, 1985, pp. 160-168.
[13] Chang, S., Rioux, M., and Domey J.,” Face recognition with range images and intensity image,” Optical Engineering, vol.36, no.4 , April 1997, pp.1106-1112.
[14] Chawla S., Shekhar S., Wu, W., and Ozesmi, U., “Modeling spatial dependencies for mining geospatial data: An introduction,” 2000 .
[15] Cho, S.Y. and Chow, T. W. S., “Neural Computation Approach for Developing 3-D Shape Reconstruction Model,” IEEE Tran. On Neural Networks, vol. 12, no. 5, Sep, 2001, pp. 1204-1214.
[16] Dovgard, Roman, Basri, Ronen,“Statistical Symmetric Shape from Shading for 3D Structure Recovery of Faces,” European Conference on Computer Vision (ECCV), 2004.
[17] Draper, B.A., Baek, K., Bartlett, M.S.,and Beveridge, J.R., “Recognizing Faces with PCA and ICA,” Computer Vision and Image Understanding, vol. 91, no. 1-2, July/August, 2003, pp. 115-137.
[18] Elagin, E., Steffens, J. and Neven, H., “Automatic Pose Estimation System for Human Faces based on Bunch Graph Matching Technology,” Procedings of the Third International Conference on Automatic Face and Gesture Recognition, 1998, pp. 136-141.
[19] Eriksson, Anders, Weber, David, “Towards 3-dimensional Face Recognition,”IEEE Proceedings of 5th ICON, 1999, pp.401-406.
[20] Foerstner,W.,”In the geometric precision of digital correlation,” International Archives of Photogrammetry , Vol.24, 1982, pp. 176-189.
[21] Georghiades, S., Belhumeur P. N., and Kriegman, D. J.,“ From few to many: illumination cone models for face recognition under variable lighting and pose,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 23, 2001, pp. 643-660.
[22] Golomb, B. A., and Sejnowski , T. J., “SexNet: A neural network identifies sex from human faces,” in Advances in Neural Information Processing Systems 3D.
[23] Gordon,” Face recognition based on depth maps and surface curvature,” Geometric Methods in Computer Vision, vol. 1570, no. 1-12, July 1991.
[24] Goudail, G., Lange, E., Iwamoto, T., Kyuma, K., and Otsu, N., “Face Recognitio System Using Local Autocorrelations and Multiscale integration,” IEEETrans. On Pattern Analysis and Machine Intelligence, vol. 18, no. 10, 1996, pp. 1024-1028.
[25] Grimson, W.,”Computational experiments with a feature based stereo algorithm,” IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI, vol. 7, no. 1, 1985, pp. 17-34.
[26] Grudin, M.A., “On Internal Representations in Face Recognition Systems,” Pattern Recognition, vol. 33, no. 7, 2000, pp.1161-1177.
[27] Gruen, A., “Adaptive least square correlation: A powerful image matching technique,” ISPRS Journal of Photogrammetry, Remote Sensing and Cartography ,vol.14 , no.3, 1985, pp.175-187.
[28] Gruen, A., and Agouris, P.,”Linear extraction by least squares template matching constrained by internal forces,” Proceedings fo ISPRS Commission III Symposium on Spatial Information from Digital Photogrammetry and Computer Vision, vol. 509, no.30, 1994, pp.316-232.
[29] Hesher, A. Srivastava, and Erlebacher , G., “A novel technique for face recognition using range images,” Seventh Int''l Symp. on Signal Processing and Its Applications, 2003.
[30] Hong Z., “Algebraic feature extraction of image for recognition,” Pattern Recognition Letters, vol. 24, no. 3, 1991, pp. 211-219.
[31] Hotelling, H. “Analysis of a complex of statistical variables into principal components,” Journal of Educational Psychology, vol 24, 1993, 498-520.
[32] J. A. McLaughlin and J. Raviv, “Nth-order autocorrelations in pattern recognition,” Information and Control, vol. 12, 1968, pp. 121-142.
[33] Keogh, E.J. and pazzani, M.j., “An Enhanced Representation of Time Series Which Allows Fast and Accurate Classification,” Clustering and Relevance Feedback,” in Knowledge Discovery and Data Mining, 1998, pp.239-243.
[34] Kirby, M., and Sirovich, L., “Application of the Karhunen-Loeve producedure for the characterization of human faces,” IEEE Trans. Patt. Anal. And Mach. Intell., vol. 12, 1990, pp. 103-108.
[35] Konen, “Distortion invariant object recognition in the dynamic link architecture,” IEEE Transaction on Computers, vol. 42, no. 3, 1993, pp. 300-311.
[36] Lee, C. and Milios, E., ”Matching range images of human faces,” International Conference on Computer Vision, 1990, pp. 722.726.
[37] Lee, S.-H. and Leou, J.-J.,”A dynamic programming approach to line segment matching in stereo vision,” Pattern Recognition, vol.27, no.8,pp., 1994, pp. 961-986.
[38] Lew, M.S., Huang, T.S., Wong, K.W.,”Learning and feature selection in stereo matching,” IEEE Transactions on Pattern Analysis and Machine Intelligence , vol. 16, no.9, 1994, pp.869-881.
[39] Matsumoto, Y. and Zelinsky, A., “An Algorithm for Real-time Stereo Vision Inplementation of Head Pose and Gaze Direction Measurement,” Proceedings of the Fourth International Conference on Automatic Face and Gesture Recognition(FG’00), 2000, pp. 499-504.
[30] Medioni, G. and Nevatia, R., “Segment based stereo matching,” Computer Vision Graphics and Image Processing , vol. 31, 1985, pp. 2-18.
[41] Ohta, Yuichi, and Kanade, Takeo.,”Stereo by intra-and-inter-scanline search using dynamic programming,” IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-7 (2), 1985, pp.139-154.
[42] Otsu, N. and Kurita, T., “A New Scheme for Practical, Flexible and Intelligent Vision Systems,” Proc. IAPR Workshop on Computer Vision-Special Hardware and Industrial Applications, 1988, pp. 431-435.
[43] Pentland, A., “Looking at People: Sensing for Ubiquitous and Wearable Computing,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 1, 2000, pp.107-119.
[44] Popovici, V., Thiran, J.-P.;Neural Networks for Signal Processing, 2002. Proceedings of the 2002 12th IEEE Workshop on , 4-6.
[45] Prokoski, F., Riedel, R., Coffin, J.,”Identification of individuals by means of facial thermography,” Security Technology, 1992, pp.120-125.
[46] Ruicheck, Y. and Postaire, J.-G. ,”A neural implementation for high speed processing in linear stereo vision,” IEEE International Conference on Systems Man and Cybernetics , Vol.5, 1995, pp.3902-3907.
[47] Samal, A., and Iyengar, P., “Automatic recognition and analysis of human faces and facial expressions: A survey,” Patt. Recog., vol. 25, 1992, pp.65-77.
[48] Sirovich L.and Kirby, M., “Low-Dimensional Procedure for Characterization of Human Faces,” J. Optical Soc. Am., vol. 4, 1987, pp. 519-524.
[49] Steven D. Cochran and Gererd Medioni, ctober”, 3-D Surface Description from Binocular Stereo,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 14, no.10, 1992.
[50] Tsalakanidou, Tzovaras, D. and Strintzis, M. G., ”Use of depth and colour eigenfaces for face recognition,” Pattern Recognition Letters, vol. 24, no. 9-10 , June, 2003, pp.1427-1435.
[51] Turk, M., and Pentland, A., “Eigenfaces for Recognition,” J. Cognitive Neuroscience, vol. 3, no.1, 1991, pp.71-86.
[52] Valentin , D., Abdi, H., O’Toole, A.J., and Cottrell G.W., “Connectionist Models of Face Processing: a Survey,” Pattern Recognition, vol. 27, no. 9, 1994, pp.
1209-1230.
[53] Wiskott, L., Fellous, J.M., Kru, N., and der Malsburg, C. von, “Face Recognition by Elastic Bunch Graph Matching,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 7, 1997, pp. 775-779.
[54] Yuen, P.C. and Lai, J.H., “Face Representation Using Independent Component Analysis,” Pattern Recognition, vol. 35, no. 6, 2002, pp. 1247-1257.
[55] Zhao, L. and Yang, Y., “Theoretical Analysis of Illumination in PCA-Based Vision Systems,” Pattern Recognition, vol. 32, no. 4, 1999, pp. 547-564.

會議論文
[56] Achermann, Jiang, X., and Bunke, H., ”Face recognition using range images,”International Conference on Virtual Systems and Multimedia, 1997, pp. 129-136.
[57] Cartoux, Y., LaPreste, J. T., and Richetin, M., ” Face authentication or recognition by profile extraction from range images,” Proceedings of the Workshop on Interpretation of 3D Scenes, Nov. 1989, pp.194-199.
[58] Cottrell, G. and Flerning, M.,“Face Recognition Using Unsupervised Feature Extraction,” Proceedings of 1990 International Neural Network Conference, Paris, France, 1990, pp. 322-325.
[59] Hotta, K., Kurita, T. and Mishima, T., “Scale Invariant Face Detection Method using Higher-Order Local Autocorrelation Features extracted from Log-Polar Image,” in automatic Face and Gesture Recognition. Proceedings. Third IEEE International Conference on, IEEE, 1998, pp. 70-75.
[60] Hung, Kwok-Wah, and Chan, Wing-Chung , “Stroke encoded Chinese handwriting input system based on back-propagation networks,” TENCON ''93. Proceedings. Computer, Communication, Control and Power Engineering.1993 IEEE Region 10 Conference on, vol.2, 1993, pp. 1106 - 1109.
[61] Kurita, T., Otsu, N., and Sato, T., “A Face Recognition Method Using Higher Order Local Autocorrelation and Multivariate Analysis,” Proc, 11th IAPr int’l conf. Pattern Recognition, 1992, pp. 213-216.
[62] Lao, S., Sumi, Y., Kawade, M., and F. Tomita,”3D template matching for pose invariant face recognition using 3d facial model built with iso-luminance line based stereo vision,” In International Conference on Pattern Recognition (ICPR 2000), 2000, pp. 911-916.
[63] Lengagne R., Fua, P., Monga, O.,”3D Face Modeling from Stereo and Differential Constraints,” Proceedings. Third IEEE International Conference on, 1998, pp.14-16.
[64] Lengagne, R., Fua, P., Monga, O.,”Using differential constraints to generate a 3D face model from stereo,” Proceedings. Fourteenth International Conference on , vol.1 , Aug. ,1998, pp.637 – 639.
[65] Moreno B., S´anchez, Angel, V´elez , J. F., and J.D´iaz , F.,”Face recognition using 3D surface-extracted descriptors,” Irish Machine Vision and Image Processing Conference, September, 2003.
[66] Mousavi, M. S. and Schalkoff, R. J., "A parallel distributed algorithm for feature extraction and disparity analysis of computer images," Proceedings of IEEE Computer Society Conference on Computer Vision on Pattern Recognition, 1990, pp.428-435.
[67] Nagamine, T., Uemura, T., and Masuda, I.,” 3D facial image analysis for human identification,” International Conference on Pattern Recognition (ICPR 1992), 1992, pp. 324-327.
[68] Penev, P.S., and Sirovich, L., “The Global Dimensionality of Face Space,” Proc. Fourth IEEE Int’l Conf. Automatic Face and Gesture Recognition, 2000, pp. 264-270.
[69] Pentland, A., Moghaddam, B., Starner, T., and Turk, M., “View-based and modular eigenspaces for face recognition,” in Proc. IEEE Computer Soc. Conf on Computer Vision and Patt. Recog., 1994, pp. 84-91.
[70] Popovici, V., and J. P., Thiran, “Higher Order Autocorrelations for Pattern Classification,” in Proceedings of the International Conference on Image Processing(ICIP), 2001.
[71] Tanaka, T., Ikeda, M., and Chiaki, H.,”Curvature-based face surface recognition using spherical correlation principal directions for curved object recognition,” Third International Conference on Automated Face and Gesture Recognition,1998, pp. 372-377.
[72] Turk, M. A., and Pentland, A. P., “Face recognition using eigenfaces,” in Proc. Int. Conf. on Patt. Recog., 1991, pp. 586-591.
[73] Yang, M.H., “Kernel Eigenfaces vs. Kernel Fisherfaces: Face Recognition Using Kernel Methods,” Proc. Fifth IEEE Int’l Conf. Automatic Face and Gesture Recognition (RGR’02), 2002, pp. 215-220.
[74] Zhang, Liming and Donghui Qu, “A neural network structure for feature extraction and recognition of handwritten digits,” Conference Proceedings, China., 1991 International Conference on ,vol.1, no. 16-17, 1991, pp.294 - 297.

學位論文
[75] 汪慶祥，利用三維資訊做人臉辨識，國立交通大學，資訊科學研究所，碩
士論文，2000。
[76] 洪贊原，運用雙影像視覺與特徵臉於人臉辨識, 國立國立臺北科技大學碩士論文，2004。
[77] 陳冠臻，以影像為依據建立三維立體模型，國立中山大學，資訊工程學系研究所，碩士論文，2000。
[78] 陳衍亨(2002)，利用人臉影像的三維資訊作身分驗證，國立交通大學，資訊科學系，碩士論文。