隨著電腦速度提升，即時人臉辨識的可能性大幅提升，相關的研究論文與應用產品的數量不可勝數，而現今常用的臉部辨識的方法有：主值成份分析(PCA)、彈性束圖匹配(EBGH)、支持向量機預測學習(SVM)等方法。

不論是何種人臉辨識方法，如能事先得知人臉在影像中的位置，將會提升人臉辨識的處理速度與辨識準確度。故本論文使用一種即時、不需訓練、適用於大部分人種的人臉定位系統。

該系統先以上半圓霍夫定位抓取影樣中近似上半圓的物體，並利用膚色偵測的方式檢測該上半圓物體是否為膚色物體，再利用人臉膚色的幾何位置特性進行次定位，在次定位後得到一塊搜尋區域，利用人嘴在人臉區域中顏色最紅的特性，檢測該區是否存在人嘴，若搜尋範圍內沒有出現人嘴，則判定該區為非人臉區域，若該搜尋區域通過嘴部檢測，則標記為人臉，進行眼部定位後結束人臉定位。

在本論文將會簡單介紹影像處理的基本知識與現今常用的定位方法，並在系統中採用人臉特徵的方式定位人臉。最後實驗測試本系統人臉定位，分析此方法的優點與缺點。

With the computer processing speed increases, the possibility of real-time face recognition rises widely. Research papers and application products which relate to face recognition are also countless. Nowadays, there are several common methods used for face recognition which are principle component analysis (PCA), elastic bunch graph matching (EBGM), support vector machines (SVM), etc.

If a system could predict the face location in an image before processing this image, it will improve the performance of processing speed and recognition rate; therefore, this thesis proposes a real-time, no-training face detection system which suit to most people.

This thesis uses a method which uses upper-circle Hough transform to locate the upper-circle-like object(s) and detect whether it is a skin-color-like object(s) by using skin color detection. Using the character that the lip is the reddest region on face, the proposed method could indicate whether this is face region for sure by applying sub-detection. The final step is the eye detection which makes the detected face region more precise.

In this thesis, the basic background of image processing and the most used face detection methods will be mentioned first. Then, it will introduce the feature-based face detection methods. Finally, it will analysis the advantages and disadvantages through experiments.

[1] D. A. Forsyth and J. Ponce, Computer Vision – A MORERN APPROACH, publishing as Prentice Hall.
[2] 鍾國亮 教授 著「影像處理與機器視覺 2/e」，東華書局出版
[3] R. C. Gonzalez and R. E. Woods, Digital Image Processing 2/e, publishing as Prentice Hall.
[4] R. C. Gonzalez and R. E. Woods, Digital Image Processing using MATLAB, publishing as Prentice Hall.
[5] http://www.face-rec.org
[6] M. Turk, A. Pentland, “Eigenfaces for Recognition,” Journal of Cognitive Neurosicence, v 3, n. 1, pp. 71-86, 1991.
[7] L. Wiskott, J. M. Fellous, N. Krueuger, C. von der Malsburg, “Face Recognition by Elastic Bunch Graph Matching,” Chapter 11 in Intelligent Biometric Techniques in Fingerprint and Face Recognition, eds. L.C. Jain et al. , pp. 355-396, CRC Press, 1999.
[8] J. Canny, “A computational approach to edge detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 8(6), pp.679-698, 1986.
[9] P. V. C. Hough “Method and means for recognizing complex patterns,” U. S. Patent 3, 069, 654, Dec. 18, 1962.
[10] 黃泰祥，具備人臉追蹤與辨識功能的一個智慧型數為監視系統，中原大學電子工程系碩士學位論文，西元2005
[11] M. Soriano, S. Huovinen, B. Martinkauppi, and M. Laaksonen, “Using the Skin Locus to Cope with Changing Illumination Conditions in Color-Based Face Track,” Proc. of IEEE Nordic Signal Processing Symposium, pp. 383-386, 2000.
[12] C. Y. Tang, Y. P. Hung, and Z. Chen, “Automatic detection and tracking of human heads using an active stereo vision system,” International Journal of Pattern Recognition and Artificial Intelligence, v 14, n 2, pp. 137-166, 2000.
[13] R. L. Hsu, M. Abdel-Mottaleb, and A. K. Jain, “Face Detection in Color Images,” IEEE Transactions on Pattern Analysis and Machine Intelligence, v 24, pp.696-706, 2002.
[14] 陳愛斌，複雜背景下基於Hough變換的人臉定位，中國圖像圖型期刊，中圖分類號TP391.41，文獻標識碼A，文章編號1009-2552(2004)04-0024-03，2004
[15] R. O. Duda and P. E. Hart, “Use of the Hough transformation to detect lines and curves in pictures,” Commun. ACM, 15(1) , pp 11-15, 1972.
[16] P. Viola and M. J. Jones, "Rapid Object Detection using a Boosted Cascade of Simple Features," in Proceedings of the IEEE Computer Society International Conference on Computer Vision and Pattern Recognition, v 1, pp. 511-518, Dec. 2001.
[17] 謝怡竹，以光流為基礎之自動化表情辨識系統，國立中央大學，西元2005
[18] S. Baskan, M. M. Bulut, V. Atalay. “Projection based method for segmentation of human face and its evaluation,” Pattern Recognition Letters 23, pp.1623-1629, 2002.
[19] J. Yang, R. Stiefelhagen, U. Meier, and A. Waibel. “Real-time face and facial feature tracking and applications,” Proceedings of the International Conference on Auditory-Visual Speech Processing AVSP'98, pp. 79--84, 1998.
[20] A. L. Yuille, D. S. Cohen, P. W. Hallinan, “Feature Extraction from Faces Using Deformable Template,” CVPR, 1989.
[21] T. D Orazio, M. Leo, G.Cicirelli, A. Distante, “An Algorithm for real time eye detection in face images,” ICPR (3) pp.278-281, 2004.
[22] 黃銘裕，眼位追蹤─型變濾波器，國立台灣大學電機研究所，西元2000
[23] 王國強，人眼追蹤系統及其於人機介面之應用，國立中央大學資訊工程所，西元2003
[24] 莊莉，徐光祐，艾海舟，梁路宏，彭振雲，視頻中多線索的人臉特徵檢測與跟蹤，北京 100084
[25] http://vis-www.cs.umass.edu/~vidit/AI/dbase.html
[26] D. Anifantis.;E. Dermatas; G. Kokkinakis “A neural network method for accurate face detection on arbitrary images,” Proc Conference on Electronics, Circuits and Systems, Pafos, Cyprus, v 1, n 5-8, pp.109- 112, Sep. 1999.
[27] G. Guo, S.Z. Li, and K. L. Chan, “Support vector machines for face recognition,” Image and Vision Computing, v 19, n 9-10, pp.631-638, Aug 1, 2001.
[28] C. W. Hsu and C. J. Lin, “A comparison of methods for multiclass support vector machines,” IEEE Transactions on Neural Networks, v 13, n 2, pp.415-425, Mar, 2002.
[29] Y. J. Wang, C. S. Chua, and Y. K. Ho, “ Facial feature detection and face recognition from 2D and 3D images,” Pattern Recognition Letters, v 23, n 10, pp.1191-1202, Aug, 2002.
[30] P. N. Belhumeur, J. P. Hespanha, and D. J. Kriegman, “Eigenfaces vs. fisherfaces: recognition using class specific linear projection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, v 19, n 7, pp.711-720, Jul, 1997.