人臉偵測對於「臉孔辨識」、「駕駛睡眠偵測」與「智慧型人機介面」等應用是非常重要的，最近幾年來更是受到大家的廣泛重視。這些應用的首要工作在於找出人臉的所在區域，因此如何正確而可靠的找出人臉位置是相當重要的。在本論文提出了一個新的 大小的邊緣遮罩，同時利用可調式閥值的調整，對輸入的影像進行特徵邊緣檢測，可以突顯出欲偵測之人臉眼部、鼻孔及嘴部的水平方向性邊緣特徵。首先將影像利用小波轉換消除雜訊及降低解析度，由本文提出的新的邊緣檢測方法，建立臉部的水平方向性邊緣特徵，再利用多層次特徵模板進行眼部及嘴部的特徵比對，進而將正確的人臉位置標示出來。

Human face detection is very important in its wide range of applications, such as human face recognition, drowsiness detection, human-computer interface, etc. In most such applications, the existence of human faces and their correct locations must be found. In other words, a reliable and correct method for detecting and locating human face region is considerably significant. In this paper, a new 1x7 mask for edge detection combining the adjustment of adapted threshold values is proposed. In this way, we can increase the edge orientation features of eyes and mouths. First, the wavelet transform is used to reduce the noise and the dimension. Second, a new 1x7 mask is employed to build the horizental edge features. Third, a multilayer face template is used to match the horizental edge features of faces. Finally, a reliable and correct method is developed to locate human face region.

摘要………………………………………………………………………I
Abstract………………………………………………………………II
致謝……………………………………………………………………IV
目錄………………………………………………………………………V
圖目錄…………………………………………………………………VII
表目錄……………………………………………………………………X
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系統目標與限制………………………………………………3
1.4論文架構………………………………………………………4
第二章 相關研究探討………………………………………………5
2.1人臉偵測的困難……………………………………………5
2.2人臉偵測的研究……………………………………………6
第三章 邊緣特徵的擷取…………………………………………11
3.1相關邊緣偵測的方法…………………………………………11
3.2新的邊緣偵測方法……………………………………………14
3.3可調式閥值的建立……………………………………………21
3.4多層次人臉模板特徵比對……………………………………27
第四章 人臉偵測系統……………………………………………37
4.1影像輸入前處理………………………………………………37
4.2邊緣特徵建立…………………………………………………39
4.3人臉邊緣特徵比對……………………………………………40
第五章 實驗結果…………………………………………………44
5.1系統環境………………………………………………………44
5.2資料庫與測試結果……………………………………………45
5.3錯誤分析………………………………………………………51
5.4與其他系統比較結果…………………………………………52
第六章 結論與未來發展…………………………………………54
參考文獻…………………………………………………………56
圖目錄
圖1.1 人臉偵測系統處理流程……………………………………………3
圖2.1 臉部特徵模型………………………………………………………7
圖2.2 利用類神經網路來偵測人臉………………………………………10
圖3.1 利用不同遮罩對影像處理的結果…………………………………12
圖3.2 使用Sobel 經過不同閥值處理後之邊緣影像………………13
圖3.3 眼部、鼻子及嘴部中水平邊緣的變化……………………………15
圖3.4 水平遮罩…………………………………………………16
圖3.5 水平遮罩對眼睛、鼻子及嘴部處理之結果………………………17
圖3.6 水平遮罩對整張影像處理的結果…………………………………18
圖3.7 垂直、左傾45 度及右傾45 度之個別遮罩………………………20
圖3.8 垂直及左、右傾45 度之基本樣板及對整張影像的運算結果……20
圖3.9 過小或過大的閥值所產生的影響…………………………………21
圖3.10 採用固定閥值所產生的影響………………………………………22
圖3.11 直接進行輸入影像之區域切割所產生之誤差……………………23
圖3.12由定義之子全域平均值與區域平均值…25
圖3.13 利用模糊理論建立的可調式閥值，依權值或調整…………27
VIII
圖3.14 人臉邊緣特徵模型………………………………………………28
圖3.15 人臉模板的邊緣像素分布………………………………………30
圖3.16 眼睛、鼻子及嘴部各區域之邊緣像素分佈相互比較…………31
圖3.17 眼睛、鼻子及嘴部個別區域之邊緣像素特性分布……………32
圖3.18 鼻樑二側與眼睛下方之水平邊緣變化…………………………33
圖3.19 人臉特徵比對流程圖……………………………………………34
圖3.20 多層次特徵模板比對流程………………………………………36
圖4.1 小波轉換之多層解析的階層式架構………………………………38
圖4.2 二維離散小波轉換…………………………………………………39
圖4.3 經由水平遮罩處理後之水平邊緣特徵…………………40
圖4.4 人臉偵測標示區域重疊……………………………………………41
圖4.5 第一階段完成人臉偵測……………………………………………42
圖4.6 第二階段完成人臉偵測……………………………………………43
圖5.1(a)系統畫面………………………………………………………44
圖5.1(b)系統畫面………………………………………………………45
圖5.2(a)JAFFE 資料庫範例………………………………………………46
圖5.2(b)BioID 資料庫範例………………………………………………46
圖5.2(c)FERET 資料庫範例………………………………………………47
IX
圖5.3(a)JAFFE 偵測正確範例……………………………………………48
圖5.3(b)BioID 偵測正確範例……………………………………………48
圖5.3(c)FERET 偵測正確範例……………………………………………49
圖5.4(a)JAFFE 偵測錯誤圖片範例………………………………………49
圖5.4(b)BioID 偵測錯誤圖片範例………………………………………49
圖5.4(c)FERET 偵測錯誤圖片範例………………………………………50
圖 5.5(a) 經由webcam擷取320x240影像之測試結果…………………50
圖 5.5(b) 由電視卡擷取256x384影像之測試結果……………………51
圖5.6 C.L.Shen 系統偵測錯誤圖片範例………………………………53
表目錄
表5.1 資料庫偵測結果……………………………………………………46
表5.2 C.L.Shen 系統偵測之結果…………………………………………53

[1]A. M. Bagci, R. Ansari, A. Khokhar, ” Eye tracking using markov models” IEEE Proceedings of the 17th International Conference on Pattern Recognition 2004.
[2] Bernhard Fr¨oba and Christian K¨ublbeck, “Robust face detection at video frame rate based on edge orientation features” Automatic Face and Gesture Recognition, 2002. Proceedings. Fifth IEEE International Conference on May 20-21 2002 pp. 327 – 332.
[3]Cheng-Chin Chiang and Chi-Lun Huang, “A neural-based surveillance system for detecting dangerous non-frontal gazes for car drivers” IEICE Trans. ine&syst vol E87-D,no.9 septmember 2004.
[4] Chun-Ming Li, Yu-Shan Li, Qing-De Zhuang, Zhong-Zhe Xiao, “ The face localization and regional features extraction“ Proceedings of the Third International Conference on Machine Learning and Cybernetics, Shanghai, August 26-29 2004
[5]E. Osuna, R. Freund, and F. Girosi, “Training support vector machine: An application to face detection”, Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 1997, pp.130-136.
[6]G. Yang and T.S. Huang, “ Human face detection in a complex background”, Pattern Recognition, vol.27, no.1, 1994, pp.53-63.
[7] Henry A. Rowley, Shumeet Baluja, Takeo Kanade, ” Neural network-based face detection” IEEE transaction on pattern analysis and machine intelligent, vol. 20, no. 1, January 1998.
[8]H. P. Graf, T. Chen, E. Petajan, and E. Cosatto, “Locating faces and facialparts”, Proc. First Int’l Workshop Automatic Face and Gesture Recognition, 1995, pp. 41-46.
[9]H. Wu, Q. Chen, and M. Yachida, “Face detection from color images using a fuzzy pattern matching method”, IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 21, no. 6, June 1999, pp.557-563.
[10]I. Craw, H. Ellis, and J. Lishman, “Automatic extraction of face features”, Pattern Recognition Letters, vol. 5, 1987, pp. 183-187.
[11]K.K. Sung, “ Learning and example selection for object and pattern detection”, PhD thesis,MIT AI Lab,1996.
[12]K. K. Sung and T. Poggio, “Example-based learning for view-based human face detection”, IEEE Trans. on pattern analysis and machine intelligence 20, 1998, pp. 39-51.
[13] Kohsia S. Huang and Mohan M. Trivedi , ” Robust real-time detection, tracking, and pose estimation of faces in video streams” Proceedings of the 17th International Conference on Pattern Recognition 2004.
[14]K. Scobottka and I. Pitas, “Face localization and feature extraction base on shape and color information”, Proc. of IEEE Int’l Conf. on Image Processing, 1996, pp. 483-486.
[15]J. Miao, B. Yin, K. Wang, L. Shen, and X. Chen, “A hierarchical multiscale and multiangle system for human face detection in a complex background using gravity-center template”, Pattern Recognition, vol. 32, no. 7, 1999, pp. 1237-1248.
[16]L. Sirovich, and M. Kirby, “Low-dimensional procedure for the characterization of human faces”, J. Opt. Soc. Amer. 4, 1987, pp. 519-524.
[17]M. F. Augusteijn and T. L. Skujca, “Identification of human faces through texture-based feature recognition and neural network technology”, Proc. IEEE Conf. Neural Networks, 1993, pp. 392-398.
[18]M. Turk and A. Penland, “Egienfaces for recognition”, Journal of Cognitive Neuroscience, vol. 3, March 1991, pp. 71-86.
[19] Muhammad Hassan Khan, Dr. Nadeem A. Khan, Arif Zuberi(2004),” Fast and accurate localization of human faces” Intemational Symposium on Communications and Information Technologies 2004 ( ISClT 2004 ) Sapporo, Japan, October 26- 29, 2004.
[20] P. Shin, and C. Liu, “Face detection using discriminating feature analysis and support vector machine”, Pattern Recognition Society, 2005.
[21]Q. Chen, H. Wu, and M. Yachida, “Face detection by fuzzy mating”, Proc. Fifth IEEE Int’l Conf. Computer Vision, 1995, pp. 591-596.
[22]S. A. Sirohey, “Human face segmentation andidentification”, Technical Report CS-TR-3176, Univ. of Maryland, 1993.
[23]T. K. Leung, M.C. Burl, and P. Perona, “Finding faces in cluttered scenesusing random labeled graph matching”, Proc. Fifth IEEE Int’l Conf. Computer Vision, 1995, pp. 637-644.
[24]T. Sakai, M. Nagao, and S. Fujibayashi, “Line Extraction and pattern Detection in a Photograph”, Pattern Recognition, vol, 1, 1969, pp. 233-248.
[25] Xiaoyun Deng, Chip-Hong Chang, Erwin Brandle, ”A new method for eye extraction from facial image” Proceedings of the Second IEEE International Workshop on Electronic Design, Test and Applications 2004.
[26]Y.H. Chan and S.A.R. Abu-Bakar, ” Face detection system based on feature based chrominance colour Information” IEEE Proceedings of the International Conference on Computer Graphics, Imaging and Visualization 2004.
[27]C.T. Hsieh and C.L. Shen, “Real time face detection system”, National Computer Science(NCS), Dec.2003, Taiwan, pp. 1049-1056.