有很多的方法可以用來做面像辨識，這些的方法是建立在給定的面像樣本上面。而當輸入的臉部影像需要用到簡單的幾何轉換和光度的調整時，這些方法的成效就不是很令人滿意。在這篇論文中，將提出一個新面像辨識的方法，它可以自動的消除平移，旋轉，放大縮小和投射變換，還可以消除光度。根據臉部的特徵點，用這個方法可以找到最優的幾何轉換和光度的影響，然後在消除它們來辨識及找尋和目標最接近的樣本。最後在辨識的時候是採用最小平方法來辨識。

There exist many methods for facial recognition, such as
eigenface, templates, artificial neural networks, etc., based on the given facial sample data (patterns). When an input facial image (target) involve simple geometrical transformations and illumination, the performance of these methods are not very satisfactory. In this thesis, following Li et al., we propose a new face recognition system, which can eliminate translation, rotation, scaling, and prospective transformations of facial images automatically, and can also eliminate illumination. According to facial features, we use this method to find the best transformation and the closet illumination, and then to eliminate them for identification by the best matching between a target and the patterns. Finally, we
use the least squares method to recognize the target. This method is validated by numerical examples.

1. Introduction...........................................1
2. Basic Algorithms ......................................2
3. Perspective Transformation ............................6
4. Illumination Effects .................................10
5. Graphical and Numerical Experiments ..................12
6. Final Remarks ........................................15
Reference ...............................................16

[1] Barnsley, M. F., Fractals Everywhere, 2nd edition, Academic Press, New York, 1993.

[2] Brunelli, R. and Poggio, T., Face recognition through geometrical features, Proc. ECCV 588, 792 - 800, 1992.

[3] Brunelli, R. and Poggio, T., Face recognition: features versus templates, IEEE Trans. PAMI 15 (10), 1042 - 1052, October 1993.

[4] Buhmann, J., Lades, M. and Malsburg, C.v.d., Size and distortion invariant object recognition by hierarchical graph matching, Proceedings of the International Joint Conference on Neural Networks, pp. 411 - 416, 1990.

[5] Cappellini, V. and Marconi, R., (Eds.), Advance in Image Processing and Pattern Recognition, Elsevier Science Publishers, North-Holland, Amsterdam, 1986.

[6] Chellappa, R., Wilson, C. L. and Sirohey, S., Human and machine recognition of faces: a survey, Proceedings of the IEEE, 83(5): 705 - 740, 1995.

[7] Daugman, J., "Face and gesture recognition: Overview", IEEE Trans. Pattern Analysis and Machine Intelligence, 19(7): 675 - 676, 1997.

[8] Graham, D. B. and Allinson, N. M., Face recognition using virtual parametric eigenspace signatures, IEE conf. Publication (Part 1) (443), 106 - 110, 1997.

[9] Hall, E. L., Computer Image Processing and Recognition, Academic Press, New York, 1979.

[10] Kanade, T., Computer Recognition of Human Faces, Birkhauser, Basel and Stuttgart, 1977.

[11] Kirby, M. and Sirovich, L., Application of the karhunen-loeve procedure for the characterization of human faces, IEEE Trans. PAMI 12 (1) 103 - 108, 1990.

[12] Krzyzak, A., Kasvand, T. and Suen, C. Y., Computer Vision and Shape Recognition, World Scientific Publishing Co. Ltd., Singapore, New Jersey, 1989.

[13] Lades, M., Vorbruguen, J., Buhmann, J., Lange, J., Malsburg, C.v.d. and Wurtz, R., Distortion invariant object recognition in the dynamic link architecture, IEEE Trans. Comput. 42, 300 - 311, 1993.

[14] Lam, K. M. and Yan, H., An analytic-to-holistic approach for face recognition based on a single frontal view, IEEE PAMI 20 (7), 673 - 686, July 1998.

[15] Lawrence, S., Giles, C. L., Tsoi, A. C. and Back, A. D., Face recognition: a convolutional neural network approach, IEEE Trans. Neural Networks, Special Issue on Neural Networks Pattern Recognition 8 (1), 98 - 113, 1997.

[16] Li, Z. C., Bui, T. D., Tang, Y. Y. and Suen, C. Y., Computer Transformation of Digital Images and Patterns, World Scientific, Singupose, P. 27, P 93, 1989.

[17] Mandelbrot, B., The Fractal Geometry of Nature, Freeman, San Francisco, CA, 1982.

[18] Modenov, P. S. and Parkhomenko, A. S., Geometric
Transformation: Projective Transformation, Academic Press, New York and London, Vol. 2, 1965.

[19] Pantic, M. and Rothkrantz, L. J. M., "Automatic analysis of facial expressions: the state of the art", IEEE Transactions on Pattern Analysis and Machine Intelligence 22(12): 1424 - 1445, 2000.

[20] Pentland, A., Moghaddam, B., Starner, T. and Turk, M., View-based and modular eigenspaces for face recognition, Proceedings of the IEEE Computer Society Confence on Computer Vision and Pattern Recognition, pp. 84 - 91, 1994.

[21] Samal, A. and Iyengar, P. A., "Automatic recognition and analysis of human faces and facial expressions: A survey", Pattern recognt., Vol 25, pp. 65 - 77, 1992.

[22] Shackleton, M. A. and Welsh, W. J., Classification of facial features for recognition, IEEE Computer Vision and Pattern Recognition, pp. 573 - 579, 1991.

[23] Tan, X., Chen, S., Zhou, Z. H. and Zhang, F., Face recognition from a simgle image per person: A survey, Technical report, Department of Computer Seience and Engineering, Nanjing University of Aercnantics Astronauticsm Nanjing 210016, China, 2005.

[24] Tan, T. and Yan, H., Object recognition based on fractal neighbor distance, Signal Processing, Vol 81, P 2105 - 2129, 2001.

[25] Tan, T. and Yan, H., The fractal neighbor distance measure, Pattern Recognition, Vol 35, PP 1371 - 1387, 2002.

[26] Turk, M. and Pentland, A., Eigenfaces for recognition, J. Cognitive Neurosci. 3 (1), 71 - 86, 1991.

[27] Turk, M. and Pentland, A., Face recognition using eigenfaces, Proceeding of the IEEE Conderence on Computer Vision and Pattern Recognition, pp. 586 - 591, 1991.

[28] Valentin, D., Abdi, H. et al., "Connectionist models of faceprocessing: a survey", Pattern Recognition, Vol 27, No. 9, pp. 1209 - 1230, 1994.

[29] Vasilescu, M. Alex. O. and Terzopoulos, D., Multinear image analysis for facial recognition, Inter Conf on Pattern Recognition, ICPR'02, Quebec city, Canada, August, 2002.

[30] Yang, M. H., Kriegman, D. and Ahuja, N., Detecting face in images: A survey, IEEE Trans. Patt. Anal. Mach. Intell. 24, 34 - 58, 2002.

[31] Young, T. Y. and Fu, K. S., (Eds.), Handbook of Pattern Recognition and Image Processing, Academic Press, Orlando, Florida, 1986.

[32] Yuille, A. L., Deformable templates for face recognition, J. Cognitive Neurosci. 3 (1), 59 - 70, 1991.

[33] Zhang, J., Yan, Y. and Lades, M., Face recognition: eigenface, elastic matching, and neural nets, Proc. IEEE 85 (9), 1423 - 1435, September 1997.

[34] Zhao, W., Chellappa, R., Phillips, P. J. and Rosenfeld, A., "Face Recognition: A Literature Survey", ACM Computing Survey, December Issue, pp. 399 - 458, 2003.