人臉偵測作為人與電腦交流(human-computer interaction)的第一步，目的是要從一張圖片或影像中找出人臉確切的位置，進而能拿來作為其他用途。找出圖上的人臉位置對人類來說是理所當然的事情，可是對電腦來說卻是一項挑戰，於是到現在為止已經有無數的研究在這一方面。本篇論文中會探討各種方法，並且分析各方面的優缺點，並選出優秀的方法來進行實作。將所有的方法區分成四大類型，從大的範圍縮小到Appearance-based Approach 類型的方法，這是在這十年多來進步最多的方法。再進一步探討其中，然後集中探討Boosting類型的演算法，最後從裡面選出Vector Boosting實作其演算法，並且進行改良的研究。本篇論文對Vector Boosting提出的改良方法可以非常有效的節省訓練所需要花的時間，而不會減低測試圖片的效能。

As the first step of human-computer interaction, face detection is a research topic in recent years. The subject is to finding face position in an image or video, and then we can use the as for other purposes. Finding a face on an image is a matter of course for people, but it is a challenge to computers. Until now, there have been numerous studies in this field. In this paper, we will survey different face detection methods, and the advantages and disadvantages of these methods would be analyzed. Finally we will choose an excellent methods and implementation the algorithm. All of the face detection methods can be divided into four categories, and then the range narrowed down to Appearance-based Approach, which is the most improved in this decade. The next step analyzes on Appearance-based Approach, and focus on boosting algorithm. Eventually, we choose vector boosting and implement its algorithm, try to find a way to improve it. We come up to a way that can save a lot of time in training, without lost the performance in testing.

[1] Y. Abramson and B. Steux, “YEF* Real-Time Object Detection,“ International Workshop on Automatic Learning and Real-Time, 2005.
[2] S. C. Brubaker, J. Wu, J. Sun, M. D. Mullin, and J. M. Rehg, “On the Design of Cascades of Boosted Ensembles for Face Detection,” Technical report, Georgia Institute of Technology, GIT-GVU-05-28, 2005.
[3] Cortes, Corinna, and Vapnik, Vladimir N., "Support-Vector Networks", Machine Learning, 20, 1995.
[4] B. Fr¨oba and A. Ernst, “Fast Frontal-View Face Detection Using a Multi-Path Decision Tree,” Proc. of Audio- and Video-based Biometric Person Authentication, 2003.
[5] C. Huang, H. Ai, Y. Li, and S. Lao, “Learning Sparse Features in Granular Space for Multi-View Face Detection,” Intl.Conf. on Automatic Face and Gesture Recognition, 2006.
[6] C. Huang, H. Ai, Y. Li, and S. Lao, ”Vector Boosting for Rotation Invariant Multi-View Face Detection,” Proc. of ICCV,2005.
[7] M. Jones and P. Viola, “Fast Multi-View Face Detection,” Technical report, Mitsubishi Electric Research Laboratories, TR2003-96, 2003.
[8] C. Kotropoulos and I. Pitas, “Rule-Based Face Detection in Frontal Views,” Proc. Int’l Conf. Acoustics, Speech and Signal Processing, vol. 4, pp. 2537-2540, 1997.
[9] Lanitis, C.J. Taylor, and T.F. Cootes, “An Automatic Face Identification System Using Flexible Appearance Models,” Image and Vision Computing, vol. 13, no. 5, pp. 393-401, 1995.
[10] T.K. Leung, M.C. Burl, and P. Perona, “Finding Faces in Cluttered Scenes Using Random Labeled Graph Matching,” Proc. Fifth IEEE Int’l Conf. Computer Vision, pp. 637-644, 1995.
[11] R. Lienhart, A. Kuranov, and V. Pisarevsky, ”Empirical Analysis of Detection Cascades of Boosted Classifiers for Rapid Object Detection,” Technical report, Microprocessor Research Lab, Intel Labs, 2002.
[12] R. Lienhart and J. Maydt, “An Extended Set of Haar-Like Features for Rapid Object Detection,” Proc. of ICIP, 2002.
[13] S. Li, L. Zhu, Z. Zhang, A. Blake, H. Zhang, and H. Shum, “Statistical Learning of Multi-View Face Detection,” Proc. Of ECCV, 2002.
[14] Liu and H.-Y. Shum, “Kullback-Leibler Boosting,” Proc. Of CVPR, 2003.
[15] W. S. McCulloch and W. H. Pitts, “A Logical Calculus of the Ideas Immanent in Nervous Activity,” Bulletin of Mathematical Biophysics, 5:115–133, 1943.
[16] T. Mita, T. Kaneko, and O. Hori, “Joint Haar-Like Features for Face Detection,” Proc. of ICCV, 2005.
[17] T. Ojala, M. Pietikäinen, and D. Harwood (1996), "A Comparative Study of Texture Measures with Classification Based on Feature Distributions," Pattern Recognition, vol. 29, pp. 51-59.
[18] Opelt, A. Pinz, and A. Zisserman, “A Boundary-Fragment-Model for Object Detection,” Proc. of CVPR, 2006.
[19] P. Pudil, J. Novovicova, and J. Kittler, “Floating Search Methods in Feature Selection,” Pattern Recognition Letters, 15(11):1119–1125, 1994.
[20] R. E. Schapire,” The Strength of Weak Learnability,” Machine Learning, vol. 5, no. 2, pp. 197-227, 1990.
[21] P. Sinha, “Object Recognition via Image Invariants: A Case Study,” Investigative Ophthalmology and Visual Science, vol. 35, no. 4, pp. 1735-1740, 1994.
[22] P. Viola and M. Jones, “Rapid Object Detection Using a Boosted Cascade of Simple Features,” Proc. of CVPR, 2001.
[23] X. Wang, T. X. Han, and S. Yan, “An HOG-LBP Human Detector with Partial Occlusion Handling,” Proc. of ICCV, 2009.
[24] Wu, H. Ai, C. Huang, and S. Lao, “Fast Rotation Invariant Multi-View Face Detection Based on Real Adaboost,” Proc. of IEEE Automatic Face and Gesture Recognition, 2004.
[25] R. Xiao, L. Zhu, and H. Zhang, “Boosting Chain Learning for Object Detection,” Proc. of ICCV, 2003.
[26] Z. Yang and H. Ai, “Demographic Classification with Local Binary Patterns,” Int. Conf. on Biometrics, pages 464–473, 2007.
[27] G. Yang and T. S. Huang, “Human Face Detection in Complex Background,” Pattern Recognition, vol. 27, no. 1, pp. 53-63, 1994.
[28] M.H. Yang, Kriegman, D.J. and Ahuja N., “Detecting Faces in Images: a Survey,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.24, NO.1, pp. 34-58, Jan. 2002.
[29] K.C. Yow and R. Cipolla, “Feature-Based Human Face Detection,” Image and Vision Computing, vol. 15, no. 9, pp. 713-735, 1997.
[30] H. Zhang, "The Optimality of Naive Bayes," FLAIRS2004 conference.
[31] Zhang and Z. Zhang, “A Survey of Recent Advances in Face Detection,” Microsoft Research Tech. Report, June 2010.