臺灣博碩士論文加值系統

目前人臉辨識其方法很多如：主成分分析、類神經網路、小波轉換等等。傳統人臉辨識做法是將一張彩色人臉影像轉換成灰階影像再做特徵擷取動作，但這樣會遺失影像本身的彩色信息，導致辨識率下降，故本論文為了保留影像的彩色信息，直接對彩色影像做處理，其主要方法是以四元數Zernike不變矩擷取影像之特徵，並搭配單純貝氏分類器分類特徵值，使用資料庫為face94和IMM的彩色人臉資料庫來實現人臉辨識。首先，輸入人臉影像，經過一些影像前處理如：像素正規化、調整影像大小、轉成YCbCr色彩模型，再以旋轉和平移的不變性四元數Zernike矩擷取人臉影像的特徵值，最後利用單純貝氏分類器將特徵值分類來判斷該人臉影像，並比較搭配其他分類器之結果。
關鍵字：彩色人臉辨識、四元數Zernike不變矩

There are many face recognition methods such as principal component analysis (PCA), neural network and wavelet transform etc. recently. Conventional methods to deal with color face image are transformed to gray or binary image, which may loss some significant color features lead to accuracy rate descending. In order to preserve the image color information we use quaternion Zernike moment invariant extracted feature that directly process in color space and with the naïve Bayes classifier recognition. Two database we used in this paper, they are IMM database and face94 database to achieve face recognition. At first a preprocessing for color face images is performed, including pixel normalization, image resizing and color space transform. Second, the quaternion Zernike moment invariants are used to extract face image feature. Finally the naïve Bayes classifier is used to recognition face image and we also compare the results with other classifiers.


Keyword：color face recognition, quaternion Zernike moment invariants

致謝 I
摘要 II
ABSTRACT III
目錄 IV
圖目錄 VI
表目錄 IX
第一章 緒論 1
1-1 研究動機 1
1-2 研究目的 2
1-3 論文架構 3
第二章 數位影像處理 4
2-1 彩色影像 4
2-2 色彩模型 6
2-2-1 HSV色彩空間 6
2-2-2 YIQ色彩模型 9
2-2-3 YCbCr色彩模型 10
2-3 影像內插法 12
2-4 四元數 17
第三章 影像特徵值擷取 18
3-1 色彩空間特徵 18
3-2 特徵值擷取 19
3-2-1 不變矩 19
3-2-2 Zernike矩和四元數Zernike不變矩 22
第四章 分類技術 29
4-1 判別分析 29
4-2 單純貝氏分類器 30
第五章 人臉辨識系統 33
5-1 系統架構與流程 33
5-2 實驗環境 34
5-3 實驗結果 35
第六章 結論與未來展望 51
6-1 結論 51
6-2 未來展望 52
參考文獻 53

[ 1 ]Son Lam Phung, A. Bouzerdoum, D. Chai, “A novel skin color model in YCbCr color space and its application to human face detection”, International Conference on Image Processing, vol. 1, pp. 289–292, 2002.
[ 2 ]Wei Pan, YiJia Huang, “A new algorithm of face detection under strong light condition”, International Conference on Advanced Computer Control, vol. 3, pp. 487–491, Mar. 2010.
[ 3 ]Canhui Cai, S.K. Mitra, “A normalize color difference edge detector based on quaternion representation”, Image Processing, International Conforence on, vol. 2, pp. 816–819, Sep. 2000.
[ 4 ]S.J. Sangwine, “Color image edge detector based quaternion convolution”, Electronics Letters, vol. 34, pp. 969–971, May 1998.
[ 5 ]C.H. The, R.T. Chin, “On image analysis by the methods of moments”, IEEE Transaction on, Pattern Analysis and Machine Intelligence, vol. 10, no. 4, pp. 496–513, Jul. 1988.
[ 6 ]Ming-Kuei Hu, “Visual pattern recognition by moments invariants”, IRE Transactions on Information Theory, vol. 8, no. 2, pp. 179–187, Feb. 1962.
[ 7 ]Y. Sheng, L. Shen., “Orthogonal fourier-mellin moments for invariant pattern recognition”, J. Opt. Soc. Am. A, vol. 11, No. 6, pp. 1748–1757, 1994.
[ 8 ]S.A. Dudani, K.J. Breeding, R.B. McGhee, “Aircraft Identification by Moment Invariants”, IEEE Transaction on Computers, vol. 26, no. 1, pp. 39–46, Jan. 1977.
[ 9 ]A.P. Reeves, R.W. Taylor, “Identification of three-dimensional objects using range information”, IEEE Transaction on Pattern Analysis and Machine Intelligence, vol. 11, no. 4, pp. 403–410, Apr. 1989.
[ 10 ]M.R. Teague, “Image analysis via the general theory of moments”, Journal of the Optical Society of America, vol. 70, no. 8, pp. 920–930, 1980.
[ 11 ]C. Maaoui, H. Laurent, C. Rosenberger, “2D color shape recognition using Zernike moments”, IEEE International Conference on Image Processing, vol. 3, pp. 976–979, Sep. 2005.
[ 12 ]Dengsheng Zhang, Guojun Lu, “Improving retrieval performance of Zernike moment descriptor on affined shapes”, IEEE International Conference on Multimedia and Expo, vol. 1, pp. 205–208, 2002.
[ 13 ]Whoi-Yul Kim and Yong-Sung Kim, “A region-based shape descriptor using Zernike moments”, Signal Processing: Image Communication, vol. 16, pp. 95–102, Sep. 2000.
[ 14 ]A. Khotanzad and Y.H. Hong, “Invariant image recognition by Zernike moments”, IEEE Transaction on Pattern Analysis and Machine Intelligence, vol. 12, no.5, pp. 489–497, May 1990.
[ 15 ]Ye Bin and Peng Jia-Xiong, “Invariance analysis of improved Zernike moments”, Journal of Optics A: Pure and Applied Optics, vol. 4, no. 6, pp. 606–614, Sep. 2002.
[ 16 ]R. Bailey and M. Srinath, “Orthoognal moment features for use with parametric and non-parametric classifiers”, IEEE Transaction on Pattern Analysis and Machine Intelligence, vol. 18, pp. 389–399, Apr. 1996.
[ 17 ]Beijing Chen, Huazhong Shu, Hui Zhang, Gang Chen, Limin Luo, “Color image anlysis by quaternion Zernike moments”, International Conference on Pattern Recognition, pp. 625–628, Aug. 2010.
[ 18 ]Fei Ye, Zhiping Shi, Zhongzhi Shi, “A comparative study of PCA,LDA and Kernel LDA for Image Classification”, International Symposium on Ubiquitous Virtual Reality, pp. 51–54, Jul. 2009.
[ 19 ]Qi Tian, Jie Yu, Ting Rui, T.S. Huang, “Parameterized discriminant analysis for image classification”, IEEE International Conference on Multimedia and Expo, vol. 1, pp. 5–8, Jun. 2004.
[ 20 ]William H. Press, Saul A. Teukolsky, William T. Vetterling, Brian P. Flannery, Numerical Recipes. The Art of Scientific Computing.(Third Edition), Cambridge University Press, 2007.
[ 21 ]Sergios Theodoridis and Konstantinos Koutroumbas, Pattern Recognition. (4th Edition), Academic Pr, 2010.
[ 22 ]W.R. Hamilton, Elements of quaternions. Longmans Green, London, U.K., 1866.
[ 23 ]W.J. Krzanowski, Principles of Multivariate Analysis, Oxford University Press, Oxford, 1988.
[ 24 ]G.A.F. Seber, Multivariate Observations, Wiley, New York, 1984.
[ 25 ]F. Zernike, Physica, vol. 1, pp. 689–704, 1934.
[ 26 ]Rafael C. Gonzalez, Richard E. Woods 原著，繆紹剛 譯，數位影像處理(Digital image processing, 2nd ed.)，台灣培生教育，民92年。
[ 27 ]繆紹剛，數位影像處理-活用Matlab，全華，民88年。
[ 28 ]繆紹剛，數位影像處理-運用Matlab，東華書局，民93年。
[ 29 ]徐曉珮，數位影像處理(McAndrew:Introduction to Digital Image Processing with MATLAB)，高立出版，民98年。
[ 30 ]http://www2.imm.dtu.dk/~aam/ (IMM人臉資料庫)
[ 31 ]http://cswww.essex.ac.uk/mv/allfaces/faces94.html (face94人臉資料庫)