本論文針對PCA、ICA和它們的變形─2DPCA、FICA，以及LDA等數種以基底影像之線性組合來表示原影像的辨識方法進行多項人臉辨識實驗。本論文主要的貢獻是發展一個共同的性能比較平台，並探討影像前處理和各個辨識方法搭配不同距離量測方式對於人臉辨識結果的影響，進而找出在不同情況下較適用的方法。本論文使用了兩種資料庫來進行實驗，第一種是由FERET資料庫所提供的原始影像剪裁而來，第二種是自製的小型資料庫。實驗結果除了証實影像前處理具提昇人臉辨識效果外，亦發現FICA和LDA之辨識率的相似以及2DPCA和LDA不同的適用場合。

Many face recognition experiments have been conducted in this thesis to compare the performance among several face recognition algorithms including PCA, ICA and their variants (2DPCA, FICA), as well as LDA, in which these algorithms employ the linear combinations of the basis images to represent the original image. One of the major contributions of this thesis is to develop a common platform that can be used to compare the performance among different face recognition algorithms under the same criterion. The other contribution is to investigate the effects of image preprocessing and recognition algorithms with different performance metrics on face recognition results so that the user can choose a suitable algorithm for a specific application. Two databases are used in the experiments. One is adapted from the FERET database, while the other is a self-made small-scale database. Experimental results not only verify that image preprocessing indeed can improve the performance of face recognition algorithms but also show the similarity between the recognition rates of FICA and LDA as well as different application scenarios of 2DPCA and LDA.

[1] M. Turk and A. Pentland, “Eigenfaces for recognition,” J. Cognitive Neurosci., vol. 3, no. 1, pp. 71-86, 1991.
[2] P. N. Belhumeur, J. P. Hespanha, and D. J. Kriegman, “Eigenfaces vs. Fisherfaces: Recognition using class specific linear projection,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 19, no. 7, pp. 711-720, Jul. 1997.
[3] M.S. Bartlett, J.R. Movellan, and T.J. Sejnowski, “Face recognition by independent component analysis,” IEEE Trans. Neural Networks, vol. 13, no. 6, pp. 1450-1464, Nov. 2002.
[4] Keun-Chang Kwak and Witold Pedrycz, “Face recognition using an enhanced independent component analysis approach,” IEEE Trans. Neural Networks, vol. 18, no. 2, pp. 530-541, Mar. 2007.
[5] B. Moghaddam, “Principal manifolds and probabilistic subspaces for visual recognition,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 24, no. 6, pp. 780-788, Jun. 2002.
[6] B. A. Draper, K. Baek, M. S. Bartlett, and J. R. Beveridge, “Recognizing face with PCA and ICA,” Comput. Vis. Image Understanding, vol. 91, pp. 115-137, 2003.
[7] Jian Yang, David Zhang, Alejandro F. Frangi, and Jing-yu Yang, “Two-dimensional PCA: A new approach to appearance-based face representation and recognition,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 1, pp. 131-137, Jan. 2004.
[8] R. C. Gonzalez and R. E. Woods, Digital Image Processing, Prentice Hall, 2002.
[9] A. and E. Oja, “Independent component analysis: algorithms and applications,” Neural Networks, vol. 13, pp. 411-430, 2000.
[10] David C. Lay, Linear Algebra and Its Applications, Addison Wesley, 2005.
[11] A. J. Bell and T. J. Sejnowski, “An information-maximization approach to blind separation and blind deconvolution,” Neural Comput., vol. 7, no. 6, pp.1129-1159, 1995.
[12] Robert J. Schalkoff, Pattern Recognition: Statistical, Structural and Neural Approaches, John Wiley and Sons, 1991.
[13] Jian Yang and Chengjun Liu, ”Horizontal and vertical 2DPCA-based discriminant analysis for face verification on a large-scale database,” IEEE Trans. Information and Security, vol. 2, no. 4, pp. 781-792, Dec. 2007.
[14] P. J. Phillips, H. Wechsler, J. Juang, and P. J. Rauss, “The FERET database and evaluation procedure for face recognition algorithms,” Image Vision Comput. J., vol. 16, no. 5, pp. 295-306, 1998.