臺灣博碩士論文加值系統

目前針對人臉的偵測與辨識的研究主題是非常熱門。截至目前為止，要使機器能在含有人臉的影像中完全偵測出人臉，仍然是一個很困難的問題。在許多我們實際生活的應用上（例如：個人身分證上所使用的識別照片），人臉影像所採用的背景通常是很單純的。本論文中，我們提出了以邊緣輪廓資訊為基礎的人臉偵測方法。要有高的人臉偵測率必須是單純的色彩背景、姿勢與表情。這個方法，首先借助直方圖均勻量化加強輸入影像，附加一些影像方面的前置處理後，接著由邊緣偵測濾波器抽出臉部邊緣輪廓資訊。實驗結果證實這個方法是有很好的效能。

Human face detection and recognition is a very popular research subject. Up to the present, it is still a hard problem to detect a human face as an image by machine, if the image contains some faces. In many practical applications (e.g. personal identification using photo-IDs), face images generally contain a simple background. In this thesis, we propose a face detection method based on the information from the edge shapes. High face detection rate can be obtain under the simple color background, posture and countenance. Input image is first enhanced by means of histogram equalization, adding some preprocess to improve the performance for our face detection system, followed by edge detection. The face contour is finally extracted using the edges information. Experimental results are showed to verify the collectness effectiveness of this method.

第一章 緒論 1
1.1 背景與動機 1
1.2 為什麼要做人臉偵測？ 2
1.3 人臉偵測的應用 3
1.4 人臉偵測的困難點 4
1.5 論文架構 5
第二章 人臉偵測的相關理論基礎 6
2.1 人臉偵測簡介 6
2.2 人臉偵測的方法 6
2.3近似人臉（average face）的方法 8
2.4 特徵基礎（feature-based）的方法 11
2.5 類神經網路（neural network）的方法 14
2.6色彩基礎（color-based）的方法 16
2.7人臉偵測方法的討論 19
第三章 基本影像處理技巧 21
3.1影像的範疇 21
3.2數位影像之優點 22
3.3影像處理之基本運算 22
3.3.1 像素運算 (pixel operation) 22
3.3.2轉換運算 (transform operation) 23
3.4數位影像之灰階亮度 23
3.4.1灰階亮度統計圖 (histogram) 24
3.4.2 動態分佈範圍 (dynamic range) 的大小 26
3.4.3適合影像分割處理之灰階亮度統計圖 27
3.4.4對比強化運算 29
3.5迴旋積法 29
3.5.1 遮罩運算 29
3.5.2遮罩之迴旋積 (convolution) 運算 30
3.6邊緣強化—蝕刻與膨脹運算 31
第四章 邊緣資訊之人臉偵測系統 33
4.1 系統基本架構描述 33
4.2影像加強(image enhancemen) 35
4.3中值濾波(median filtering) 36
4.4整形濾波 38
4.5邊緣偵測(edge detection) 41
4.6圖樣相配（template matching） 47
第五章 實驗步驟與結果分析 52
5.1 實驗環境 52
5.2 系統架構流程 53
5.2.1改變圖樣大小的詳細步驟 53
5.2.2 偵測系統的詳細步驟 54
5.3 實驗結果 54
5.3.1偵測時間 57
5.3.2偵測正確率 57
5.3.3偵測結果 58
5.4 實驗結果分析 71
第六章 結論與未來工作 73
6.1 結論 73
6.2 未來工作 75
參考文獻 76

[1] H.H. Bothe and E.A. Wieden, “A neurofuzzy approach for modeling lips movements”, IEEE World Congress on Computational Intelligence, pp. 234–237, 1994.
[2] S. Uthiram, G. Bebis and M. Georgiopoulos, “Genetic search for face detection and verification”, 1999 International Conference on Information Intelligence and Systems, pp. 360–367, 1999.
[3] H. Y. Wu, Q. Chen and M. Yachida, “ Face detection from color images using a fuzzy pattern matching method”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.21, No.6, pp. 557–563, June 1999.
[4] H. Nugroho, S. Ozawa, S. Takahashi, Y. Ooi, “Detecting human face from monocular image sequences by genetic algorithm”, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 2533–2536, 1997.
[5] Z. Bian, H. Peng, C. Zhang, “Human eyes detection using hybrid neural method”, 1998 Fourth International Conference on Signal Processing Proceedings, pp. 1088–1091, 1998.
[6] D. A. Seongiong, C. J. Park, J. Seo, “Detection of human faces using skin color and eyes”, 2000 IEEE International Conference on Multimedia and Expo, pp.133–136, 2000.
[7] E. A. Johnson and C. H. Wu, “A real-time fuzzy logic-based neural facial feature extraction technique”, In Proceedings of the Third IEEE Conference on Fuzzy Systems, vol. 1, pp. 268–273, June 1994.
[8] J. Miao and B. C. Yin, “A hierarchical multiscale and multiangle system for human face detection in a complex background using gravity-center template”, Pattern Recognition 32(10), pp. 1237–1248, 1999.
[9] R. Cipolla and K. C. Yow, “Feature-based human face detection”, Image and Vision Computing, vol. 15, no. 9, pp. 713–735. 1997.
[10] R. L. Hsu, A. M. Mohamed and A. K. Jain, “Face detection in color images”,IEEE Transactions on pattern analysis and machine intelligence, Vol.24, No.5, May 2002
[11] G. Yang and T. Huang, “Human Face Detection in a Complex Background”, Pattern Recognition, Vol. 27. No. 1, pp.53–63, 1994.
[12] Eigenfaces and Gaussian Pyramids, http://cns.bu.edu/~lavanya/Graphics/cs585/p2/p2.html
[13] Webdweller - Home of the average human face,
http://www.octapod.org.au/webdweller/averageface/
[14] Four Approaches to Face Detection, http://turing.csie.ntu.edu.tw/~bj/facedet/report.html
[15] C. C. Han, H. Y. Mark Liao, K. C. Yu, and L. H. Chen, “Fast Face Detection via Morphology-based Pre-processing”, Academia Sinica, Taipei, Taiwan.
[16] K. C. Yow, R. Cipolla, “Feature-Based Human Face Detection”, Department of Enginneering,Cambridge
[17] K. Toyama, G.Haga. “Incremental focus of attention for robust visual tracking.”, IN Computer Vision and Patt. Recog., pp. 189-195,1996.
[18] B. Fasel, B.Y. Souleil, J. Luettin and M. M. Stphane, “Fast Multi-Scale Face Detection”, IDIAP-Com 98-04, 1998.
[19] 譚永恒, “以數位影像處理技術做人臉自動追蹤系統”,全國博碩士論文
[20] 人臉偵測(Human Face Detection), http://www.chu.edu.tw/~m8802517/
[21] The Face Home Page, http://debut.cis.nctu.edu.tw/~ching/Face/face.htm
[22] Matlab在影像處理上的應用http://ace136.auto.fcu.edu.tw/eduteach/imagexp/index.html
[23] http://www.mathworks.com.
[24] 繆紹綱, “數位影像處理 活用Matlab”,全華科技圖書,民89。