人臉偵測是一項具挑戰性的工作，也是人臉追蹤與辨識系統之重要的前處理部份，本論文提出一套人臉偵測的方法。首先，利用膚色資訊快速地找出人臉可能存在之區域，並得到一膚色二值化圖(Skin Map)，再對此膚色二值化圖做雜訊去除的處理以及型態學的運算（浸蝕、擴張與連通元件），並利用臉部的長寬比特性過濾出可能的人臉區塊。接著，對這些可能的人臉區塊做眼睛的偵測，若找到眼睛，則利用眼睛的位置預測人臉大小並框出可能的人臉範圍，即候選臉區塊，若找不到眼睛,則視為非人臉區塊。最後，利用類神經網路，針對候選臉區塊進行臉部驗證的工作。
實驗結果顯示，本文可以有效地偵測影像中的人臉，並可以克服影像中人臉不同亮度、大小、旋轉與多人人臉的問題。

This paper proposes a human face detection system based on skin color segmentation and neural networks. The system consists of several stages. First, the system searches for the regions where faces might exist by using skin color information and forms a so-called skin map. After performing noise removal and some morphological operations on the skin map, it utilizes the aspect ratio of a face to find out possible face blocks, and then eye detection is carried out within each possible face block. If an eye pair is detected in a possible face block, a region is cropped according to the location of the two eyes, which is called a face candidate; otherwise it is regarded as a non-face block. Finally, each of the face candidates is verified by a 3-layer back-propagation neural network. Experimental results show that the proposed system results in better performance than the other methods, in terms of correct detection rate and capacity of coping with the problems of lighting, scaling, rotation, and multiple faces.

中文摘要 ........................................Ⅰ
ABSTRACT ........................................Ⅱ
目錄 ............................................Ⅲ
圖目錄 ..........................................Ⅵ
表目錄 ..........................................Ⅷ
第一章 緒論 ......................................1
1.1  	研究動機與目的 ..........................1
1.2	系統流程 ................................2
1.3	章節組織 ................................4
第二章 人臉偵測相關研究 ..........................5
2.1  	樣板比對法 ..............................6
2.2  	以特徵為基礎法 ..........................8
2.3  	以知識為基礎法 ..........................14
2.4  	機器學習法 ..............................16
第三章 候選臉區塊之搜尋 ..........................18
3.1  	可能的人臉區塊之判定 ....................18
      3.1.1   膚色偵測 ...........................18
      3.1.2   膚色分割 ...........................22
      3.1.3   過濾出可能的人臉區塊 ...............24
3.2  	擷取候選臉區塊 ..........................28
      3.2.1   	眼睛偵測與配對 .................28
		(1)  眼睛偵測 ..................28
             	(2)  眼睛配對 ..................30
      3.2.2   	擷取候選臉區塊 .................31
第四章 候選臉區塊之驗證 ..........................33
4.1	倒傳遞神經網路簡介 ......................33
  4.2  	倒傳遞神經網路訓練 ......................37
       	4.2.1  	參數設定 .......................37
       	4.2.2  	樣本取得 .......................39
       	4.2.3  	樣本正規化 .....................40
  4.3  	候選臉區塊驗證 ..........................42
第五章 實驗結果與分析 ............................44
5.1  	倒傳遞神經網路效能評估 ..................44
5.2  	人臉偵測系統實驗	.......................46 
    	5.2.1  	膚色偵測實驗 ...................48
     	5.2.2  	膚色分割實驗 ...................49
	5.2.3  	可能的人臉區塊實驗 .............50
 5.2.4  	人臉偵測結果 ............................51
5.3  	實驗結果分析.............................52
     	5.3.1  	可處理之人臉偵測問題 ...........52
     	5.3.2  	待解決之問題 ...................56
     	5.3.3  	與其他系統比較 .................58
第六章 結論與未來研究方向.........................61
6.1	結論 ....................................61
6.2      未來研究方向 ............................62
參考文獻 .........................................63


圖   目   錄
圖1.1系統流程圖 .................................3
圖3.1 Chromatic Space中的膚色分佈圖 ..............19
圖3.2 高斯模型 ..................................	19
圖3.3 	HSV色彩空間 .............................	20
圖3.4 膚色偵測結果 ..............................	21
圖3.5 	Skin map ..................................	23
圖3.6 膚色分割過程 ..............................	24
圖3.7 人臉直立狀態 ..............................	26
圖3.8 過濾出可能的人臉區塊 ......................	26
圖3.9 眼睛偵測 ..................................	29
圖3.10 眼睛與臉部的幾何關係 .....................	30
圖3.11 臉部模型 .................................	31
圖3.12 圖3.9(a)對應的候選臉區塊 ..................	32
圖4.1 倒傳遞神經網路架構 ........................	34
圖4.2 處理單元架構圖 ............................	35
圖4.3 雙彎曲函數 ................................	38
圖4.4 亮度正規化 ................................	41
圖4.5 候選臉區塊驗證流程圖 ......................	43
圖5.1 部份人臉與非人臉訓練樣本 ..................	44
圖5.2 程式介面 ..................................	47
圖5.3 單人與多人之膚色偵測結果 ..................	48
圖5.4 單人與多人之膚色分割結果 ..................	49
圖5.5 可能的人臉區塊 ............................	50
圖5.6 單人與多人之人臉偵測結果...................	51
圖5.7 不同大小的人臉偵測結果 ....................	52
圖5.8 不同亮度的人臉偵測結果 ....................	52
圖5.9 黃種人之人臉偵測結果 ......................	53
圖5.10 不同臉部表情的人臉偵測結果 ...............	53
圖5.11 不同臉部姿勢與旋轉角度的人臉偵測結果 .....	54
圖5.12 臉部部份遮蔽的偵測結果 ...................	54
圖5.13 複雜背景下的人臉偵測結果 .................	55
圖5.14 多人人臉偵測結果 .........................	55
圖5.15 影像亮度太亮與太暗導致人臉偵測失敗 .......	56
圖5.16 眼睛被頭髮遮住 ...........................	57
圖5.17 側臉偵測失敗 .............................	57
圖5.18 Fröba與Küblbeck [30]中的人臉偵測結果 .........	58
圖5.19 Fröba與Küblbeck錯誤偵測結果 ..............	60



表   目   錄
表2.1 各種人臉偵測方法之分類 .....................17
表5.1 倒傳遞神經網路分類結果 .....................45
表5.2 與Fröba及Küblbeck [30]系統比較 ...............59

[1] R. Feris, T. Campos, and R. Cesar, “Detection and Tracking of Facial Features in Video Sequences,” Lecture Notes in Artificial Intelligence, Springer-Verlag, April (2000), Vol. 1793, pp. 197-206.
[2] Y. Suzuki and T. Shibata, “Multiple-clue Face Detection Algorithm using Edge-based Feature Vectors,” Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, 2004, (ICASSP '04), May (2004), Vol. 5, 17-21, pp. V - 737-740.
[3] J. G. Wang and T. N. Tan, “A New Face Detection Method Based on Shape Information,” Pattern Recognition Letters, (2000), No. 21, pp. 463-471.
[4] Chin-Chuan Han, Hong-Yuan Mark Liao, Gwo-Jong Yu, and Liang-Hua Chen, “Fast Face Detection via Morphology-based Pre-processing,” Pattern Recognition 33, (2000), pp. 1701-1712. 
[5] 沈啟亮，即時的人臉檢測系統，碩士論文，淡江大學電機工程學系，(2004)。
[6] Toshiaki Kondo and Hong Yan, “Automatic Human Face Detection and Recognition under Non-uniform Illumination,” Pattern Recognition, (1999), Vol. 32, pp. 1707-1718.
[7] Kwok-Wai Wong, Kin-Man Lam, and Wan-Chi Siu, “An Efficient Algorithm for Human Face Detection and Facial Feature Extraction under Different Conditions,” Pattern Recognition, (2001), Vol. 34, pp. 1993-2004.
[8] P. Peer and F. Solina, “An Automatic Human Face Detection Method,” Proceedings of the 4th Computer Vision Winter Workshop (CVWW’99), Rastenfeld, Austria, (1999), pp. 122-130.
[9] F. Solina, P. Peer, B. Batagelj, S. Juvan, and J. Kovaè, “Color-based Face Detection in the “15 Seconds of Fame” Art Installation,” Proceedings of the Computer Vision/Computer Graphics Collaboration for Model based Imaging, Rendering, image Analysis and Graphical special Effects (MIRAGE 2003), INRIA Rocquencourt, France, (2003), pp. 38-47.
[10] J. Kovaè, P. Peer, and F. Solina, “Human Skin Colour Clustering for Face Detection,” Proceedings of the International Conference on Computer as a Tool, (EUROCON 2003), Ljubljana, Slovenia, September (2003), Vol. 2, pp. 144-148.
[11] Ing-Sheen Hsieh, Kuo-Chin Fan, and Chiunhsiun Lin, “A Statistic Approach to the Detection of Human Faces in Color Nature Scene,” Pattern Recognition, (2002), Vol. 35, pp. 1583-1596.
[12] Jie Yang and A. Waibel, “A Real-time Face Tracker,” Applications of Computer Vision, (WACV'96), Proceedings 3rd IEEE Workshop on 2-4 Dec. (1996), pp. 142-147.
[13] Jian-Gang Wang and Eric Sung, “Frontal-view Face Detection and Facial Feature Extraction Using Color and Morphological Operations,” Pattern Recognition Letters (20), October (1999), No. 10, pp. 1053-1068.
[14] Rein-Lien Hsu, M. Abdel-Mottaleb, and A. K. Jain, “Face Detection in Color Images,” IEEE Transaction on Pattern Analysis and Machine Intelligence, May (2002), Vol. 24, no. 5, pp. 696-706.
[15] Kwok-Wai Wong, Kin-Man Lam, and Wan-Chi Siu, “An Efficient Color Compensation Scheme for Skin Color Segmentation,” Proceedings of the IEEE International Symposium on Circuits and systems (ISCAS2003), May (2003), Vol. II, pp. 676-679.
[16] K. M. Cho, J. H. Jang, and K. S. Hong, “Adaptive Skin-color Filter”, Pattern Recognition (2001), Vol. 34, (5), pp. 1067-1073.
[17] V. Vezhnevets, V. Sazonov, and A. Andreeva, “A Survey on Pixel-Based Skin Color Detection Techniques,” Proceedings of the Graphicon-2003, (2003), pp. 85-92.
[18] Chiunhsiun Lin and Kuo-Chin Fan, “Triangle-based Approach to the Detection of Human Face,” Pattern Recognition, (2001), Vol. 34 (6), pp. 1271-1284. 
[19] Yanjiang Wang and Baozong Yuan, “A Novel Approach for Human Face Detection from Color Images under Complex Background,” Pattern Recognition, (2001), Vol. 34, No. 10, pp. 1983-1992.
[20] M. Turk and A. Pentland, “Eigenfaces for Recognition,” Journal of Cognitive Neuroscience, March (1991), Vol. 3, No. 1, pp. 71-86.
[21] S. Karungaru, M. Fukumi, and N. Akamatsu, “Human Face Detection in Visual Scenes using Neural Networks,” Transaction of IEEJ, June (2002), Vol. 122c, pp. 995-1000.  
[22] Rafael C. Gonzalez and Richard E. Woods, Digital Image Processing (2nd Edition). 
[23] 連國珍，『數位影像處理』，儒林出版。
[24] 葉怡成，『類神經網路模式應用與實作』，(2000) 4月七版，儒林出版。
[25] H. A. Rowley, S. Baluja, and T. Kanade, “Neural Network-based Face Detection,” IEEE Transaction on Pattern Analysis and Machine Intelligence, Jan. (1998), Vol. 20, pp. 23-38.
[26] 陳文俊，人臉辨識及其在家用機器人與人互動之應用，碩士論文，交通大學電機與控制工程學系，(2003)。
[27] 黃泰祥，具備人臉追蹤與辨識功能的一個智慧型數位監視系統，碩士論文，中原大學電子工程學系，(2004)。
[28] Cuizhu Shi, Keman Yu, Jiang Li, and Shipeng Li, “Automatic Image Quality Improvement for Videoconferencing,” Acoustics, Speech, and Signal Processing, 2004. Proceedings, (ICASSP '04). IEEE International Conference on Vol. 3, May (2004), pp. 701-704.
[29] The Champion dataset, http://www.libfind.unl.edu/alumni/events/champions.
[30] Bernhard Fröba and Christian Küblbeck, "Face Detection and Tracking using Edge Orientation Information", SPIE Visual Communications and Image Processing, (2001), pp.583-594