近期生物辨識被充分運用在日常生活之中，因為他有獨特的辨識性，能夠有效的分辨每一個人身上的特徵。譬如虹膜或是指紋的應用，而且有很高的應用成果，但是這些高科技的產品，所花費的成本，或是應用的地方，都會有所限制。如果使用人臉偵測的技術，便可以應用在很多的地方。因為人臉偵測的成本相對其他的生物辨識技術來的更低，而且容易應用。如:監視設備、數位相機、影像收尋或是資料影像的管理等等。近年來的生物辨識，大都應用在住家或是公司的範圍，雖然可以有效的辨識人物，但是應用卻沒有這麼廣泛。因此本論文提出一套新的人臉偵測應用的方式，可應用在自動櫃員機或是銀行出入口前。當有人員在櫃員機前領錢時，可以判斷此人員是否為一個正常的人臉，也可以判別此人臉有沒有被遮蔽物遮蔽，要是有的話，則可以第一時間通知警衛，或是當下紀錄交易時間及地點，看看是否有遭人盜用的嫌疑，進而達到一個良好且廣泛應用的安全機制。

Recently, the Biosensor system has been mostly applied to the security of the community or the company. Despite the efficiency of the identification of the human’s figure, this system isn’t applied extensively in our society. The aim of this thesis is to propose a sound human-face detection and recognition system that is different from the traditional one, which can only tell whether the figure passes the detection or not without taking any further measurement. The system proposed here can find out whether the figure is masked or not and then proceed to recognize the face. With this new function, the system can be more efficient by finding out why the recognition fails and whether the visitor is a suspect or not. Then the security guard can take further action immediately to ensure the security.

第一章	序論
   1.1 研究背景...........................................1
   1.2 研究目的...........................................2
   1.3 論文架構...........................................3
第二章  人臉偵測的相關研究
   2.1人臉偵測的困難處....................................5
2.2人臉偵測的方法及研究...................................6
       2.2.1規則式的人臉偵測方法..........................6
       2.2.2以樣板為基礎的人臉偵測方法....................7
2.2.3以表象為基礎的人臉偵測方法...........................8
  2.2.4以特徵為基礎的人臉偵測方法.........................8
第三章  影像處理
   3.1 簡介..............................................10
   3.2 顏色分割..........................................10
   3.3 色彩空間..........................................11
   3.4 影像二值化........................................15
   3.5 邊緣偵測..........................................17
   3.6 影像形態學........................................20
      3.6.1 膨脹.........................................20
      3.6.2 侵蝕.........................................22
      3.6.3 斷開和閉合...................................23
  3.7標記聯通成分........................................25
   3.8彩色影像中的空間慮波.............................. 27
      3.8.1平滑濾波器................................... 28
      3.8.2銳化濾波器................................... 30
第四章  人臉區域的偵測及特徵抓取
   4.1 臉部偵測..........................................32
      4.1.1 YCbCr空間轉換................................33
      4.1.2 膚色分割....................................36 
   4.2 臉部特徵定位......................................40
   4.2.1眼睛的初步定位...................................41
   4.2.2 嘴巴的定位......................................45
   4.3特徵擷取...........................................46
  4.3.1適應性臨界值......................................47
  4.3.2 眼睛的特徵擷取...................................48
  4.3.3嘴巴的特徵擷取....................................51
   4.4遮蔽物的辨識.......................................55
第五章  實驗結果與討論
    5.1 膚色偵測的結果...................................57
    5.2 人臉特徵點定位結果...............................60
    5.3 遮蔽物辨識的實驗結果.............................63
第六章  結論與未來展望
    6.1結論..............................................66
    6.2未來展望..........................................67
參考文獻.................................................68
圖目錄

圖3.1 (a)原始的RGB色彩空間(b)轉換為HSV色彩空間的結果......13
圖3.2 原始RGB空間轉換為YCbCr的結果........................14
圖3.3 (a)原始的RBG影像(b)對圖3.2(a)二值化後的影像.............16
圖3.4 Sobel運算子......................... ...................18
圖3.5 Sobel邊緣檢測....................... ...................19
圖3.6 膨脹的說明....................... .....................21
圖3.7 侵蝕的說明....................... .....................23
圖3.8 斷開和閉合視為是經平移之結構元素的聯集.................24
圖3.9 連通成分的標示.........................................26
圖3.10具任意係數的一個3*3遮罩...............................27
圖3.11各種尺寸的空間慮波器.................................. 29
圖3.12高通濾波器............................................ 30
圖4.1 系統架構圖.............................................31
圖4.2 人臉偵測流程圖.........................................32
圖4.3 膚色在(a)HSV及(b)YCbCr中的分布........................34
圖4.4 RGB色彩空間(左)轉YCbCr色彩空間(右)的結果.............35
圖4.5 將膚色二值化(左)及膚色擷取(右)後的結果.................38
圖4.6 偵測出的人臉區域(左)及框選出來(右)的結果...............39
圖4.7 臉部特徵區域定位的流程.................................40
圖4.8 將膚色影像(左)轉換為二值影像(右)的結果.................43
圖4.9 眼睛配對(左)及瞳孔初步定位(右)的結果...................44
圖4.10 依照比例關係初步定位眼睛及嘴巴區域....................45
圖4.11 利用雙眼重心距離作臉部特徵定位的結果..................46
圖4.12 眼睛特徵點的擷取流程..................................48
圖4.13 眼睛特徵影像擷取流程................................. 50
圖4.14 眼睛特徵點的擷取結果................................. 50
圖4.15 嘴巴特徵點的擷取流程..................................51
圖4.16 嘴巴特徵影像擷取流程..................................54
圖4.17 嘴巴特徵點的擷取結果..................................54
圖4.18 三個特徵點構成特徵三角形的示意圖......................55
圖4.19 特徵三角形的擷取結果..................................56
圖5.1 人臉偵測實驗的結果(成功)...............................58
圖5.2 人臉偵測的實驗結果(失敗)...............................59
圖5.3 人臉特徵定位的實驗結果(成功)...........................61
圖5.4 人臉特徵定位的實驗結果(失敗)...........................62
圖5.5 遮蔽物辨識的實驗結果...................................65

[1]數位影像處理，繆紹綱譯，台灣培生教育出版，台北，民國93年。

[2]數位影像處理:應用MATLAB，繆紹綱譯，台灣東華書局股份有限公司，台北，民國94年。

[3] G..Yang and T.S. Hung. “Human Face Detection in complex Background, ” Pattern Recognition, vol.27, no.1, pp. 53-63, 1994

[4] T. Sakai, M. Nagao, and S. Fujibayashi,” Line Extraction and Pattern Detection in a Photograph,” Pattern Recognition, vol.1, pp. 233-248, 1969

[5] M. Turk and A. Pentland, “Eigenfaces for Recognitim,”, vol.3, no.1, pp. 71-86 1991

[6] D. Chai and K.N. Ngan, “Locating Facial Region of a Head-and-Shoulders
Color Image,” Proc. Third Int’l Conf. Automatic Face and Gesture Recognition, pp.
124-129 , 1998.

[7] Haizhou Ai, Lihang Ying, Guangyou Xu, “A Subspace Approach to Face Detection with Support Vector Machines,” Dept. of Computer Science and Technology, Tsinghua University, Beijing.

[8] H. Rowley, S. Baluja, and T.Kanade, “Neural Network-Based Face Detection,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 1, pp.23-38, Jan. 1998.

[9] H. Wang and S.-F. Chang, “A highly efficient system for automatic face region
detection in MPGE video,” IEEE Trans. Circuits Syst. Video Technol, vol. 7, no. 4,
pp. 615-628, 1997.

[10] Christophe Garcia and Georgios Tziritas, “Face Detection Using Quantized
Skin Color Regions Merging and Wavelet Packet Analysis,” IEEE Trans. Multimedia,
vol. 1, no. 3, 1999.

[11] T. Sakai, M. Nagao, and S. Fujibayashi, “Line Extraction and Pattern Detection
in a Photograph,” Pattern Recognition, vol. 1, pp. 233-248, 1969.

[12] J. Miao, B. Yin, K. Wang, L. Shen, and X. Chen, “A hierarchical Multiscale and
Multiangle System for Human Face Detectoin in a Complex Background Using
Gravity-Center Template,” Pattern Recognition ,vol. 32, no. 7, pp. 1237-1248,
1999.

[13] I. Craw, H. Ellis, and J. Lishman, “Automatic Extraction of Face Features,”
Pattern Recognition Letters, vol. 5, pp. 183-187, 1987.

[14] Jie Yang, Weier Lu, Alex Waibel, “Skin-Color Modeling and Adaptation”
School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213, USA.

[15] Jie Yang, Alex Waibel, ”A Real-Time Face Tracker” School of Computer
Science Carnegie Mellon University Pittsburgh, PA 15213, USA.

[16] Hichem Sahbi and Nozha Boujemaa, “ Coarse to Fine Face Detection Based
on Skin Color Adaption,” INRIA Rocquencourt, France.

[17] Y. Tian, T. Kanade, and J. Cohn, “ Eye-state action unit detection by gabor wavelets” . In Proceedings of International Conference on Multi-modal Interfaces (ICMI 2000),
pages 143–150, Sept, 2000.

[18] Z. Zhang, M. Lyons, M. Schuster, and S. Akamatsu, “Comparison between
Geometry-based and Gabor-wavelets-based Facial Expression Recognition Using
Multi-layer Perceptron,” In International Workshop on Automatic Face and Gesture
Recognition, pp 454–459, 1998.

[19] Y. Tian, T. Kanade and J. F. Cohn,” Evaluation of Gabor-Wavelet-Based Facial Action Unit Recognition in Image Sequences of Increasing Complexity” , Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition, 2002

[20] Rein-Lien Hsu, Mohamed Abdel-Mottaleb, and Anil K. Jain, “Face
Detection in Color Image,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 5, pp. 696-706, May 2002.

[21] Maricor Soriano, Birgitta Martinkauppi, Sami Huovinen, and Mika Laaksonen, “Using the Skin Locus to Cope with Changing Illumination Conditions in Color-Based Face Tracking”, Proc. IEEE Nordic Signal Processing Symposium, Kolmarden, Sweden, pp.383-386, June 2000.

[22] L. Sirovich and M. Kirby,” Low-Dimensional Procedure for The Characterization of Human Face,”J.Opt. Soc. Amer. 4, 519-524. 1987

[23] Mortiz Storring, hans J. Andersen, And Erik Granum, “Skin Color Detection under Changing Lighting Condition”, 7th Sympoium on Intelligent Systems, Coimbra, Portugal, pp. 187-195, July 1999.

[24] P. Ekman, “ Facial Expression and Emotion,”Am. Psychologist, vol. 48, pp. 384-392,
1993.

[25] T. Kanade, J. Cohn, and Y. Tian, “Comprehensive Database for Facial Expression
Analysis”, Proc. Int'l Conf. Face and Gesture Recognition, pp. 46-53, Mar. 2000.

[26] J.-J.J. Lien, T. Kanade, J.F. Cohn, and C.C. Li, “Detection, tracking, and classification of action units in facial expression”, J. Robotics and Autonomous System, vol. 31, pp.131-146, 2000.

[27] K. Mase, “Recognition of facial expression from optical flow”, IEICE Trans, vol. E74, no. 10, pp. 3474-3483, Oct. 1991.

[28] Z. Zhang,“Feature-based facial expression recognition: sensitivity analysis and
experiments with a multilayer perceptron”, Int'l J. Pattern Recognition and Artificial
Intelligence, vol. 13, no. 6, pp. 893-911, 1999.

[29] 陳侑成，自動化臉孔辨識系統，立德管理學院應用資訊研究所碩士論文，民國94年。

[30] 吳瑞珍，人臉特徵自動抽取之演算法設計及應用，元智大學電機工程研究所，碩士論文，民國91年。

[31] 歐俊岳，一個以人臉影像為基礎的影像搜尋系統，台灣大學資訊工程研究所碩 士論文，民國92年。 

[32] 沈韋穎，即時人臉偵測系統，台灣大學資訊工程研究所碩士論文，民國92年。

[33] 魏育誠，結合人臉與掌形特徵之身份確認的研究，崑山科技大學電機工程研究所碩士論文，民國92年。