機器學習是一個能解決許多問題且非常有用及有效的演算法，在這篇論文中利用兩種機器學習演算法分別去偵測膚色及人臉。首先，在膚色的偵測的部份，為了解決膚色易受光源的影響，分別針對膚色群聚的特性而取的特徵，來克服光源強弱的變化及解決近似膚色的問題，在找到膚色的區域後，並得到一膚色二值化的圖，利用形態學中斷開及閉合的運算消除雜訊，再利用長及寬的比例1:4過濾出可能的區塊。在這些區塊之中使用20 x 20的滑動視窗去偵測每一個區塊中是否有人臉的存在，進一步去判別是否為左臉，正臉或者是右臉，判別的依據正是使用Adaboost去挑出特徵。在特徵的選取上，是採用Haar-like特徵及我們選擇的變異數特徵以克服光線強弱對人臉所造成的影響。
實驗結果顯示，可以克服光線強弱對膚色造成的影響，及偵測人臉旋轉，及多人臉。

The machine learning is the state-of-the-art algorithm to solve all kinds of problems. This paper utilizes two types of machine learning algorithm to detect skin and face respectively. First, in the skin detection, to overcome the variance of light on the face is our most essential issue. According to the issue, two features chosen to serve as input of neural network dividedly, the first feature based on YCbCr to conquer the diversity of light, the second feature based on RGB to get over the color near the skin color and we get a binary map. Utilizing Opening and Closing to eliminate the noises and using the proportion of height and width to filter the candidate blocks. Second, in the face detection, the haar-like features[11][12] are utilized to serve as features of modified Adaboost to justify the left, frontal, right, or non-face in the 20 x 20 sliding window.
Experimental results show that the proposed methods reach to better performance. In terms of skin color detection, capacity of coping with the problems of scaling, rotation and multiple faces, it results in good detection rate.

目錄
第1章 緒論............................................................................................................1
1.1 研究動機與目的........................................................................................1
1.2 相關研究....................................................................................................1
第2章 相關理論....................................................................................................3
2.1 彩色模型.........................................................................................................4
2.1.1 RGB......................................................................................................4
2.1.2 YCbCr...................................................................................................5
2.1.3 HSV.......................................................................................................8
2.2 類神經網路-倒傳遞神經網路.....................................................................10
2.2.1 類神經網路的種類............................................................................11
2.2.2 類神經網路的介紹............................................................................12
2.3 AdaBoost........................................................................................................14
2.3.1 AdaBoost簡介.....................................................................................14
2.3.2 AdaBoost演算法.................................................................................15
第3章 研究方法..................................................................................................17
3.1 概要...............................................................................................................18
3.2 膚色的偵測...................................................................................................20
3.2.1 類神經網路參數設定........................................................................20
3.2.2 YCbCr特徵-第一階段........................................................................22
3.2.3 RGB特徵-第二階段...........................................................................23
3.3 AdaBoost的設計與運用................................................................................27
3.3.1 特徵選取............................................................................................27
3.3.2 弱分類器的建立................................................................................28
3.3.3 AdaBoost的訓練.................................................................................29
3.4 後處理...................................................................................................31
第4章 實驗結果與討論......................................................................................31
4.1膚色偵測系統評估........................................................................................31
4.1.1偵測錯誤的膚色.................................................................................32
4.2人臉偵測系統評估........................................................................................33
4.3 實驗結果.......................................................................................................36
第5章 結論與未來展望......................................................................................38
參考文獻......................................................................................................................38
圖 目 錄
圖2-1 RGB彩色模型..................................................................................................5
圖2-2 YCBCR顏色空間膚色分布圖........................................................................7
圖2-3 亮度在160時，膚色分布圖..........................................................................7
圖2-4 HSV顏色空間膚色分布圖及對應的顏色......................................................9
圖2-5 類神經示意圖................................................................................................10
圖2-6 倒傳遞類神經示意圖....................................................................................12
圖2-7 倒傳遞網路的網路架構圖............................................................................13
圖2-8 SIGMOID 函數式意圖....................................................................................13
圖3-1 系統流程圖....................................................................................................19
圖3-2 YCBCR特徵圖..............................................................................................23
圖3-3 膚色受外來因素影響的偵測結果................................................................24
圖3-4 膚色受光線強弱影響的偵測結果................................................................24
圖3-5 各種人種膚色的偵測結果............................................................................24
圖3-6 黑色人種膚色的偵測結果............................................................................25
圖3-7 複雜背景的偵測結果....................................................................................25
圖3-8 HAAR-LIKE特徵.............................................................................................28
圖3-9 弱分類器符號因子及門檻值........................................................................29
圖3-10 特徵的選取..................................................................................................31
圖4-1 膚色偵測結果................................................................................................32
圖4-2 膚色偵測結果................................................................................................33
圖4-3 訓練用的部分人臉及非人臉樣本................................................................34
圖4-4 修正後的正例訓練樣本................................................................................34
圖4-5 單純背景偵測結果........................................................................................36
圖4-6 複雜背景偵測結果........................................................................................37
圖4-7 左轉及右轉臉偵測結果................................................................................37
圖4-8 正臉偵測結果................................................................................................37
圖4-9 多人臉及複雜背景偵測結果........................................................................37
表 目 錄
表4-1 DETECTION RATE AND FALSE ALARM RATE比較...........................................35
表4-2 DETECTION RATE AND FALSE ALARM RATE比較...........................................36
公式 目 錄
式2-1 RGB膚色偵測門檻值......................................................................................5
式2-2 YCBCR膚色偵測門檻值................................................................................6
式2-3 YCBCR膚色偵測門檻值................................................................................8
式2-4 RGB轉換成HSV的公式..................................................................................9
式2-5 HSV膚色偵測門檻值....................................................................................10
式4-1 DETECTION RATE.............................................................................................34
式4-2 FALSE ALARM RATE.........................................................................................34

[1] Son Lam Phung, Abdesselam Bouzerdoum, Douglas Chai,“Skin Segmentation Using Color Pixel Classification: Analysis and Comparison,” IEEE Trans.on pattern analysis and machine intelligence, Vol. 27, No. 1, January 2005.
[2] J. Yang, A. Waibel, “Tracking human faces in real time,” CMU-CS-95-210, 1995.
[3] Franc Solina, Peter Peer, Borut Batagelj, Samo Juvan, Jure Kova c, “Color-based face detection in the 15 seconds of fame art
38
installation,” Proceedings of Mirage 2003, INRIA Rocquencourt, France, March, 2003.
[4] Kah Phooi seng, Andy suwandy, L. M ang, “Improved automatic face detection technique in color images,” IEEE, 2004.
[5] Yanjiang Wang, Baozong Yuan, “A novel approach for human face detection from color images under complex background,” Pattern Recognition 34 (2001) pp. 1983 – 1992.
[6] Linhui Jia and L. Kitchen, “Face Detection Using Quantized Skin Color Regions Merging and Wavelet Packet Analysis,” IEEE Transactions on Image Processing, Volume 9, Issue 1, Jan. 2000, pp. 80 – 87.
[7] Li-hong Zhao, Xiao-Lin Sun, Ji-Hing Liu, Xin-He Xu, “Face Detection Based On Skin Color,” Proceedings of the Third International Conference on Machine Learning and Cybernetics, Shanghai, August 2004.
[8] H.Wang and S-F Chang, “A highly efficient system for automatic face region detection in MPEG video,” IEEE Trans. Circuits Syst. Video Tech. vol.7 no.4, pp. 615 – 628, 1997.
[9] Min Jiang, GuiMin He, ZhaoHui Gan, “Extending active shape models with color information for facial features localization,” IEEE Int. Workshop VLSI Design & Video Tech. Suzhou, China, May 2005.
[10] Yusuke Nara, Jianming Yang, Yoshikazu Suematsu, “Face Detection Using the Shape of Face with Both Color and Edge,” Proceedings of the 2004 IEEE Conference on Cybernetics and Intelligent Systems, Singapore, December, 2004.
[11] Paul Viola, Michael Jones, “Rapid Object Detection using a Boosted Cascade of Simple Features,” Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, Dec. 2001.
[12] Paul Viola, Michael Jones, “Robust Real Time Object Detection,” IEEE ICCV Workshop Statistical and Computational Theories of Vision, July 2001.
[13] Taigun Lee, Sung-Kee Park, Mignon Park, “A New Facial Features
39
and Face Detection Method for Human-Robot Interaction,” Proceedings of the 2005 IEEE International Conference on Robotics and Automation Barcelona, Spain, April 2005.
[14] El Sayed M.Saad, Mohiy M.Hadhoud Moawad I.Moawad, Mohamed El Halawany, Alaa M. Abbas, “Detection of faces in a color natural scene using skin color classification and template matching,” 22th National Radio Science Conference March 15-17, 2005, Cairo, Egypt.
[15] Bardia Mohabbati, Shohrch Kasaci, “An Efficient Wavelet/Neural Networks-Based Face Detection Algorithm,” IEEE, 2005.
[16] Peng Wang, Qiang Ji, “Learning Discriminant Features for Multi-View Face and Eye Detection,” Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Reconnition ( CVPR 2005).
[17] Peichung Shih and Chengjun Liu,“Face Detection Using Distribution-based Distance and Support Vector Machine”, Proceedings of the Sixth International Conference on Computational Intelligence and Multimedia Applications (ICCIMA 2005).
[18] 王進德,蕭大全, “類神經網路與模糊控制理論入門” 全華科技圖書股份有限公司。
[19] Son Lam Phung, Abdesselam Bouzerdoum and Douglas Chai, “Skin Segmentation Using Color Pixel Classification: Analysis and Comparison”, IEEE Transactions on Pattern Analysis And Machine Intellegence, Vol. 27, No. 1, January 2005.
[20] Chang Huang, Haizhou AI1, Yuan LI1and Shihong Lao, “Vector Boosting for Rotation Invariant Multi-View Face Detection,” Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV’05).
[21] the CVL face database, http://lrv.fri.uni-lj.si/index.html