自動對焦為數位相機取像系統中極重要之子系統。本論文將提出一個人臉偵測方法，應用於自動對焦之自動定位功能上，使相機對焦拍出好的數位人像照片。本人臉偵測方法採用高斯混合模型(Gaussian Mixture Model)來建立人臉膚色機率模型，並以期望值最大(Expectation Maximization)方法估算高斯混合模型之參數。為克服膚色模型易受光源變化影響之問題，本方法提出一個以機率方法來建立灰階色溫曲線之自動白平衡方法，以將影像進行色溫偏差之補償修正。本系統以不同的光源、不同的焦距距離及不同的物體距離交互進行對焦區的邊緣清晰度實驗，並以量測影像品質的MTF數值進行實驗結果比較。經實驗證明本方法具有高定位之成功率，能有效的自動定位出人臉位置，完成臉部主體對焦功能。

Auto focusing is very important for digital camera system. This paper will propose a face detection method for automatic determination of focusing area, and help taking good portrait photos by the digital camera. The method adopts the Gaussian Mixture Model to train the probability model of skin color, and applies the Expectation Maximization algorithm to estimate parameters of the Gaussian Mixture Model. In order to overcome the influence of illumination change on the face detection, this paper proposes one auto white balance method by learning gray color temperature curve with a statistical method. The method compensates color temperature of the image. A comparative setup of experiments is built to verify the efficiency of the proposed method. Controlled experimental factors include illumination, distance of focus and object distance. MTF values of image quality are used to objectively evaluate the success of auto focusing after face localization. Experimental results show our method has high success rate of face localization, and effectively achieves automatic focusing.

中文摘要 i
英文摘要 ii
誌 謝 iii
目 錄 iv
表 目 錄 vi
圖 目 錄 vii
第一章 導論 1
1.1 研究動機 1
1.2 研究目的 2
1.3 文獻探討 2
1.4 論文架構 4
第二章 人臉偵測對焦系統 5
第三章 色溫校正演算法 9
3.1色溫曲線建立 10
3.2白平衡調整 16
第四章 人臉偵測方法 19
4.1 YCbCr色彩空間(YCbCr Color Space) 21
4.2高斯混合模型（Gaussian Mixture Model） 21
4.3膚色機率影像 26
4.4門檻法 ( Thresholding ) 26
4.5數學形態學 (Mathematical Morphology ) 27
4.6標示連結元件法(Connected Component Labeling, CCL) 28
第五章 實驗結果 31
5.1實驗方法 31
5.2實驗硬體架構 32
5.3實驗環境 33
5.4實驗結果 35
第六章 結論 47
參考文獻 48
附錄一 受測個體之MTF數據 51

[1] J. Baina, and J. Dublet, “Automatic Focus and Iris Control for Video Cameras,” Fifth International Conference on Image Processing and its Applications, Edinburgh, pp.232-235, 1995.
[2] H. K. Lam, O. C. Au and C. W. Wah, “Automatic White Balancing using Standard Deviation of RGB Components,” IEEE International Symposium on Circuits and Systems, Vancouver, BC, Canada, pp.III-921-4, May 2004.
[3] K. Barnard, “Improvements to Gamut Mapping Colour Constancy Algorithms,” 6th European Conference on Computer Vision, Dublin, pp.390-402, 2000.
[4] G. D. Finlayson, P. M. Hubel, S. Hordley, “Color by correlation: A simple, unifying framework for color constancy,” IEEE Trans. Pattern Anal. Machine Intelligence, vol.23, no.11, pp.1209-1221, 2001.
[5] N. K. Chern, N. P. A. Neow and M.H. Ang Jr., “Practical Issues in Pixel-Based Auto focusing for Machine Vision,” Proceedings of the IEEE International Conference on Robotics and Automation, Seoul, South Korea, vol.3, pp.2791-2796, May 2001.
[6] W. C. Kao, S. H. Wang, Y. J. Chen, C. C. Hsu and C. W. Huang, “Toward Ideal Color Image Processing Pipeline,” IPPR Conference on Computer Vision, Graphics, and Image Processing, Taiwan, Aug. 2005.
[7] G. D. Finlayson and S. D. Hordley, “Color constancy at a pixel,” Journal of the Opt. Soc. Am. A, vol.18, no.2, pp.253-264, Aug. 2001.
[8] M. H. Yang, D. J. Kriegman, and N. A. Fellow, “Detecting Faces in Images: A Survey,” IEEE Transactions on Pattern Analysis, and Machine Intelligence, vol.24, no.1, pp.34-58, Jan. 2002.
[9] E. Hjelmas, and B. K. Low, “Faces Detection: A Survey,” Computer Vision, and Image Understanding, vol.83, no.3, pp.236-274, Apr. 2001.
[10] J. Kovac, P. Peer and F. Solina, “Illumination Independent Color-Based Face Detection,” Image and Signal Processing and Analysis, Rome, Italy, vol.1, pp.510-515, Sept. 2003.
[11] S. J. Mckenna, S. Gong, and Y. Raja, “Modeling facial colour and identity with gaussian mixture,” Pattern Recognition, vol.31, no.12, pp. 1883-1892, Dec. 1998.
[12] H. Greenspan, J. Goldberger, and I. Eshet, “Mixture model for face-color modeling and segmentation,” Pattern Recognition Letters, vol.22, no.14, pp.1525-1536, Dec. 2001.
[13] G. McLachlan, and T. Krishnan, The EM algorithm and extensions, John Wiley & Sons, New York, 1997.
[14] R. C. Gonzalez, and R. E. Woods, Digital Image Processing, 2nd ed., Prentice Hall, pp.638-648, 2004.
[15] H. C. Lee, Introduction to Color Imaging Science, Cambridge, pp.234, 2005.