臺灣博碩士論文加值系統

在最近幾年來，人臉偵測已經成為一個越來越熱門的研究主題。在許多的應用上，自動化的人臉偵測也已經嚴然成為一項重要的步驟。雖然已經有眾多的方法被用來執行人臉偵測的任務，但是仍然存在著許多因素使得人臉偵測的困難度居高不下，例如人臉的大小、位置、方向、是否重疊、臉部表情及是否佩帶眼鏡等等。在這篇論文中，我們的目標是希然能夠將人臉偵測應用在視訊影像上，因此，使用者的臉部姿勢及表情是不應該被限制的。我們提出一個結合色彩、動態及臉部特徵等三部份而成的人臉偵測演算法。首先，利用一個已知的色差範圍來分割膚色區域。其次，我們根據強化後的畫面間差值，提出來一個新的方法以分割動態區域。接著，將膚色區域及動態區域合併即可獲得人臉的候選區域。再根據提出的人眼偵測策略即可在這些候選區域中找到人眼的位置。最後，我們分析每對人眼的的特性來決定這個候選區域是否為人臉的區域。
實驗結果顯示，在執行人臉偵測時，使用者可以擁有相當自由的臉部動作，例如不同的姿勢、不同的大小、不同的方向及不同的臉部表情。在速度上，提出的方法對於CIF大小的影像可以達到每秒30張的速度。除此之外，即使是佩帶眼鏡的情況之下，我們的演算法在正確率上的表現也是令人滿意的。因此可證明，提出的方法是強健、實際且有效率的。

In recent years, human face detection is becoming more and more popular. Automatically detecting human faces is becoming a very important task in various applications such as video surveillance, human computer interface, face recognition and face image database management. In the face recognition application, the human face location must be known before the processing. The face tracking application also needs a predefined face location at first. In the face image database management, the human faces must be discovered as fast as possible due to the large image database. Although numerous methods are currently used to perform the face detection, there are still many factors that make the face detection more difficult, such as scale, location, orientation, occlusion, expression and wearing glasses. Various approaches of face detection are proposed in recent years, but rare of them take all of the factors above into account. However, a face detection technique that can be used in any real time application needs to satisfy the factors above.
In this thesis, we propose a novel method to deal with the above difficulties. The objective is to detect the face region for video sequences. Therefore, the face pose should not be laminated. We propose a fast algorithm of face detection based on color, motion and facial feature analysis. Firstly, we use a set of chrominance values to obtain the skin color region. Secondly, we propose a novel method for segmenting the motion region by the enhanced frame difference. Then, we combine the skin color region and the motion region to locate the face candidates. We propose a robust eye detection method to detect the eyes in the detected face candidates region. Finally, we verify each eye pair to decide the validity of the face candidate.
According to the experiment results, the user need not be restricted when detecting the face. In general condition, the user could have wide range of face activity such as different position, size, orientation, view and facial expression. Besides, the proposed algorithm also has a satisfied detection rate even if the user is wearing glasses. The detection speed can achieve 30 frames per second for CIF sequence and 120 frames per second for QCIF sequence. Consequently, the proposed method is robust, practical and efficient.

Chapter 1 Introduction1
1.1 Background2
1.2 Applications3
1.3 Objective5
1.4 Thesis Organization7
Chapter 2 Review of Previous Works9
2.1 Knowledge-based Methods10
2.1.1 A Fast Approach for Detecting Human Faces in a Complex Background11
2.1.2 Rule-based Face Detection in Frontal Views12
2.1.3 Face Segmentation using Skin-Color Map in Videophone Applications13
2.1.4 Face Detection in Color Images16
2.1.5 Towards Facial Feature Extraction and Verification for Omni-Face Detection in Video/Images18
2.1.6 Detection of Human Faces using Skin Color and Eyes20
2.1.7 Efficient Face Detection for Multimedia Applications21
2.2 Appearance-based Methods23
2.2.1 Neural Network-Based Face Detection23
2.2.2 Face Detection in Color Images using Principal Components Analysis25
Chapter 3 The Proposed Face Detection Algorithm27
3.1 Skin Color Segmentation29
3.2 Motion Region Segmentation30
3.3 Eye Detection37
3.4 Eye Pair Validation37
Chapter 4 Experiment Results37
4.1 Motion Region Segmentation37
4.2 Test Set 137
4.3 Test Set 237
4.4 Test Set 337
4.5 Comparison with Other Methods37
4.6 Applications of Face Detection37
4.6.1 Automatic Zooming a Face Area37
4.6.2 Face-based Region of Interesting Video Coding37
4.7 Still image test37
4.8 Analysis of false and miss detections37
4.9 Discussion37
Chapter 5 Conclusions and Future Works37
5.1 Conclusion37
5.2 Future Works37
Bibliography37

[1] M. H. Yang, D. J. Kriegman and N. Ahuja, "Detecting faces in images: a survey," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 1, pp. 34-58, Jan. 2002.
[2]D. Chai and K. N. Ngan, "Face segmentation using skin-color map in videophone applications," IEEE Transactions on Circuits and Systems for Video Technology, vol. 9, no. 4, pp. 551-564, June 1999.
[3] H. 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. Rowley, S. Baluja and T. Kanade, "Neural network-based face detection," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 20, No. 1, pp. 23-38, Jan. 1998.
[5]R. L. Hsu, M. A. Mottaleb and A. K. Jain, "Face detection in color images," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 5, pp. 696-706, May 2002.
[6]C. W. Lin, Y. J. Chang and Y. C. Chen, "Low-complexity face-assisted video coding, " Proceedings of IEEE International Conference on Image Processing, vol. 2, pp. 207-210, 2000.
[7]S. L. Phung, D. Chai and A. Bouzerdoum, "A universal and robust human skin color model using neural networks," Proceedings of IEEE International Joint Conference on Neural Networks, vol. 4, pp. 2844-2849, 2001.
[8]S. Kawato and J. Ohya, "Automatic skin-color distribution extraction for face detection and tracking," Proceedings of IEEE 5th International Conference on Signal Processing (WCCC-ICSP 2000), vol. 2, pp. 1415-1418, 2000.
[9]X. Zhu, F. Jianping, A. K. Elmagarmid, "Towards facial feature extraction and verification for omni-face detection in video/images," Processings of IEEE International Conference on Image Processing, vol. 2, pp. 113-116, 2002.
[10]H. P. Graf, E. Cosatto, D. Gibbon, M. Kocheisen, E. Petajan, "Multi-modal system for locating heads and faces," Int. Conf. on Automatic Face and Gesture Recognition, pp. 88-93, Vermont, October 1996.
[11]C. Kotropoulos, A. Tefas and I. Pitas, "Frontal face authentication using morphological elastic graph matching," IEEE Transactions on Image Processing, vol. 9, pp. 555-560, April 2000
[12]Q. Yuan, W. Gao and H. Yao, "Robust frontal face detection in complex environment," Processings of IEEE 16th International Conference on Pattern Recognition, vol. 1, pp. 25-28, 2002.
[13]K. M. Lam, "A fast approach for detecting human faces in a complex background," Processings of IEEE International Symposium on Circuits and Systems (ISCAS '98), vol. 4, pp. 85-88, 31 May-3 Jane. 1998.
[14]J. Park, Jeonghee Park; Jungwon Seo; Dongun An; Seongjong Chung, "Detection of human faces using skin color and eyes," IEEE International Conference on Multimedia and Expo (ICME), vol, 1, pp. 133-136, 2000.
[15]C. Kotropoulos and I. Pitas, "Rule-based face detection in frontal views," IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-97), vol. 4, 21-24, pp. 2537-2540, April 1997.
[16]N. Tsapatsoulis, Y. Avrithis and S. Kollias, "Efficient face detection for multimedia applications," Processings of IEEE International Conference on Image Processing, vol. 2, pp. 247-250, 2000.
[17] C. Garcia and G. Tziritas, "Face detection using quantized skin color regions merging and wavelet packet analysis," IEEE Transactions on Multimedia, vol. 1, no. 3, pp. 264-277, Sept. 1999.
[18]M. Abdel-Mottaleb and A. Elgammal, "Face detection in complex environments from color images," Processings of IEEE International Conference on Image Processing (ICIP 99), vol. 3, pp. 622-626, 1999.
[19]M. H. Yang and N. Ahuja, "Detecting human faces in color images," Processings of IEEE International Conference on Image Processing (ICIP 98), vol. 1, pp. 127-130, 1998.
[20]E. Saber and A. M. Tekalp, "Face detection and facial feature extraction using color, shape and symmetry-based cost functions," Proceedings of the 13th International Conference on Pattern Recognition, vol. 3, pp. 654-658, 1996.
[21]A. adid, M. Itikainen and B. Martinkauppi, "Color-based face detection using skin locus model and hierarchical filtering," Processings of IEEE 16th International Conference on Pattern Recognition, vol. 4, pp. 196-200, 2002.
[22] K. H. Seo, W. Kim, C. Oh and J. J. Lee, "Face detection and facial feature extraction using color snake," Proceedings of IEEE International Symposium on Industrial Electronics, vol. 2, pp. 457-462, 2002.
[23] H. Wu, T. Fukumoto, Q. Chen and M. Yachida, "Face detection and rotations estimation using color information," 5th IEEE International Workshop on Robot and Human Communication, pp. 341-346, 1996.
[24] S. C. Pei and C. L. Tseng, "Robust face detection for different chromatic illuminations," Proceedings of IEEE International Conference on Image Processing, vol. 2, pp. 765-768, 2002.
[25]H. Wu, Q. Chen and M. Yachida, "Detecting human face in color images," Proceedings of IEEE International Conference on Systems, Man and Cybernetics, vol. 3, pp. 2232-2237, 1996.
[26]R. L. Hsu, M. Abdel-Mottaleb and A. K. Jain, "Face detection in color images," Proceedings of IEEE International Conference on Image Processing, vol. 1, 7-10 Oct. 2001.
[27]D. Chai and K. N. Ngan, "Automatic face location for videophone images," IEEE Region Ten Conference (TENCON'96), Perth, Australia, vol. 1, pp. 137-140, Nov. 1996.
[28] S. L. Phung, D. Chai and A. Bouzerdoum, "A skin-color classifier in YCbCr color space using multilayer perceptron," Workshop on Signal Processing Applications (WoSPA'2000), Brisbane, Australia, Dec. 2000.
[29]Y. J. Zhang, Y. R. Yao and Y. He, "Automatic face segmentation using color cues for coding typical videophone scenes," SPIE 3024, 468-479, 1997.
[30]C. C. Chiang, Y, T. Huang and Y. X. Shi, "A rule-based real-time face detector," ICS 2002 Program of Workshop on Multimedia Technology.
[31]B. Menser and F. Muller, "Face detection in color images using principal components analysis," Processings of IEEE Seventh International Conference on Image Processing and Its Applications, vol. 2, pp. 620-624, 1999.
[32]V. Solo and X. Kong, Adaptive signal processing algorithms, Prentice-Hall, pp. 32-36, 1995.
[33]J. C. Terrillon, M. N. Shirazi, H. Fukamachi, S. Akamatsu, "Comparative performance of different skin chrominance models and chrominance spaces for the automatic detection of human faces in color images" Proceedings of Fourth IEEE International Conference on Automatic Face and Gesture Recognition, pp. 54 -61,28-30 March 2000
[34]J. W. Chen, M. J. Chen and M. C. Chi, "Region of interest video coding based on face detection," Proceeding of Third IEEE Pacific Rim Conference on Multimedia, pp. 1201-1211, 2002.