臺灣博碩士論文加值系統

近年來，鑑於更有效率且更友善的人機介面之需求漸漸提高，使得各種與人臉處理相關的研究迅速地成長。除了對人提供服務之外，最重要的是系統與人們的互動關係。在本論文中，我們提出一個具有人臉追蹤與辨識功能的系統，其中於人臉追蹤的部份，利用粒子濾除器技術對人臉區域作追蹤。由於我們考慮了頭髮的顏色，當人臉背對攝影機時，系統也能持續對其作正確的追蹤。另外，我們以運動與顏色兩者資訊當作特徵，使在追蹤的過程中儘可能讓背景的影響達到最低。而在人臉辨識的部份，我們提出了一個快速辨識的方式；此作法是在人臉偵測後，由小波轉換所得到的人臉影像特徵，交給 AdaBoost演算法所訓練出來的強分類器作判斷。與其它機器學習演算法相比較，這種 AdaBoost演算法在收斂的速度上佔了很大的優勢，因此可以時常更新我們的訓練樣本以應付不同的辨識對象，同時並不會花費太大的成本；最後，我們為多類別的人臉辨識發展一個由下而上的階層式分類架構。根據實驗結果顯示，我們所提方法的人臉追蹤率在一般的情況下高於 95%，而於人臉遭受暫時性遮蔽的情況下高於 88%，又人臉的辨識率經過統計可以在 90%以上，此外，整體系統的執行效能相當令人滿意，至少達到每秒20個畫面的速度。

Owing to the demand of more efficient and friendly human computer interface, the researches on face processing have been rapidly grown in recent years. In addition to providing some kinds of service for human beings, one of the most important characteristics of a system is to naturally interact with people. In this thesis, a design and experimental study of a face tracking and recognition system is presented. Regarding the face tracking, we utilize a particle filter to localize faces in image sequences. Since we have considered the hair color information of a human head, it will keep tracking even if the person is back to a camera. We further adopt both the motion and color cues as the features to make the influence of the background as low as possible. In the face recognition phase, a new architecture is proposed to achieve fast recognition. After the face detection process, we will capture the face region and fed its features derived from the wavelet transform into a strong classifier which is trained by an AdaBoost learning algorithm. Compared with other machine learning algorithms, the AdaBoost algorithm has an advantage of facilitating the speed of convergence. Thus, we can update the training samples to deal with comprehensive circumstances but need not spend much computational cost. Finally, we further develop a bottom-up hierarchical classification structure for multi-class face recognition. Experimental results reveal that the face tracking rate is more than 95% in general situations and 88% when the face suffering from temporal occlusion. As for the face recognition, the accurate rate is more than 90%; besides this, the efficiency of system execution is very satisfactory, which reaches 20 frames per second at least.

Abstract......................................................................I
中文摘要.....................................................................II
Contents....................................................................III
List of Figures...............................................................V
List of Tables..............................................................VII
Chapter 1 Introduction........................................................1
1.1 Overview..............................................................1
1.2 Background............................................................2
1.3 Motivation............................................................3
1.4 Thesis organization and system architecture...........................4

Chapter 2 Related Works.......................................................5
2.1 Reviews of face detection and tracking................................5
2.2 Reviews of face recognition..........................................10

Chapter 3 Face Detection.....................................................13
3.1 Change detection and blob extraction.................................13
3.2 Color space transformation...........................................17
3.3 Connected component labeling.........................................22
3.4 Face detection strategies............................................25

Chapter 4 The Face Tracking Procedure........................................27
4.1 Describing and discovering the objects...............................27
4.2 The Kalman filter....................................................29
4.3 The particle filter..................................................31
4.4 Our proposed method..................................................36

Chapter 5 The Face Recognition Procedure.....................................43
5.1 Preliminary processing...............................................44
5.2 The wavelet transform................................................46
5.3 The AdaBoost algorithm...............................................50
5.4 The weak classifier..................................................56
5.5 Face recognition strategies..........................................58

Chapter 6 Experimental Results...............................................60
6.1 The results of face detection........................................61
6.2 The results of face tracking.........................................62
6.3 The results of face recognition......................................69

Chapter 7 Conclusions and Future Works.......................................76

References...................................................................79

[1] G. L. Foresti, C. Micheloni, L. Snidaro, and C. Marchiol, “Face detection for visual surveillance,” in Proceedings of the 12th IEEE International Conference on Image Analysis and Processing, pp.115-120, Sept. 2003.
[2] K. T. Song and W. J. Chen, “Face recognition and tracking for human-robot interaction,” in Proceedings of the international conference on Systems, Man, and Cybernetics, pp.2877-2882 , 2004.
[3] M. H. Yang, D. 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, 2002.
[4] G. Yang and T. S. Huang, “Human face detection in complex background,” Pattern Recognition, vol. 27, no. 1, pp. 53-64, 1994.
[5] K. C. Yow and R. Cipolla, “Feature-based human face detection,” Image and Vision Computing, vol. 15, no. 9, pp. 712-735, 1997.
[6] N. Roy, G. Baltus, D. Fox, F. Grmperle, J. Gortz, and T. Hirsch, “Towards personal service robots for the elderly,” in Proceedings of the Workshop on Interactive Robots and Entertainment, 2000; http://gs135.sp.cs.cmu.edu/papers/wire2000.pdf.
[7] A. Ohya, “Human robot interaction in mobile robot application,” in Proceedings of the 11th IEEE International Workshop on Robot and Human Interactive Communication, pp. 25-27, 2002.
[8] C. Wengert, T. Fong, S. Grange, and C. Baur, “Human-oriented tracking for human-robot interaction,” in Proceedings of the International Conference on Multimodal Interfaces, 2002.
[9] D. Chai and A. Bouzerdoum, “A Bayesian approach to skin color classification in YcbCr color space,” in Proceedings of the IEEE Region Ten Conference, vol. 2, pp. 421-424, 2000.
[10] A. 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.
[11] R. Vaillant, C. Monrocq, and Y. Le Cun “An original approach for the localization of objects in images,” in Proceedings of the IEEE Conference on Artificial Neural Networks, pp. 245-250, 1994.
[12] M. Turk and A. Pentland, “Eigenfaces for recognition,” Journal of Cognitive Neuroscence, vol. 3, no. 1, pp. 71-86, 1991.
[13] 范國清, 王元凱, 陳炳富, 追蹤演算法簡介, 影像與識別, 第8卷, 第4期, 第17-30頁, 2002.
[14] K. H. An, D. H. Yoo, S. U. Jung, and M. J. Chung, “Robust multi-viewface tracking,” in Proceedings of the IEEE International Conference on Intelligent Robots and Systems, pp. 1905-1910, 2005.
[15] S. Caifeng, W. Yucheng, T. Tieniu, and F. Ojardias, “Real time hand tracking by combining particle filtering and mean shift,” in Proceedings of the Sixth IEEE International Conference on Automatic Face and Gesture Recognition (FGR’04), pp. 669-674, 2004.
[16] S. Birchfield, “Elliptical head tracking using intensity gradients and color histograms,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 232-237, 1998.
[17] P. Fieguth and D. Terzopoulos. “Color-based tracking of heads and other mobile objects at video frame rates,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 21-27, 1997.
[18] R. M. Haralick and L. G. Shapiro, Computer and Robot Vision, vol. 2, Addison-Wesley Reading, Massachusetts, 1993.
[19] C. Y. Tang, Y. P. Hung, and Z. Chen, “Automatic detection and tracking of human head using an active stereo vision system,” in Proceedings of Asian Conference on Computer Vision, vol. 1, pp. 632-639, 1998.
[20] N. Herodotou, K. N. Plataniotis, and A. N. Venetsanopoulos, “Automatic location and tracking of the facial region in color video sequences,” Signal Processing and Image Communication, pp. 359-388, 1999.
[21] M. J. Er, S. Wu, j. Lu, and H. Lye, “Face recognition with radial basis function (RBF) neural networks,” IEEE Transactions on Neural Networks, vol. 13, no. 3, pp. 697-710, 2002.
[22] Y. Zhu, L. C. De Silva, and C. C. Ko., “Using moment invariants and HMM in facial expression recognition,” IEEE Solithivest Si~niposiirni Image Analysis and Interpretation, pp. 305-309, 2000.
[23] T. Phiasai, S. Arunrungrusmi, and K. Chamnongthai, “Face recognition system with PCA and moment invariant method,” in Proceedings of the IEEE International Symposium on Circuits and Systems, vol. 2, pp. 165-168, 2001.
[24] J. Qin and Z. S. He, “A SVM face recognition method based on Gabor-featured key points,” in Proceedings of the Fourth International Conference on Machine Learning and Cybernetics, pp. 18-21, 2005.
[25] 張龍生, 動態場景中的人物之偵測與追蹤, 碩士學位論文, 大同大學電機工程學系, 台北市, 2003.
[26] K. Y. Chen, M. Y. Cheng, and M. C. Tsai, “Design and implementation of a real-time pan-tilt visual tracking system,” in Proceedings of the IEEE International Conference on Control Applications, pp. 736-741, 2002.
[27] H. P. Graf, E. Cosatto, D. Gibbon, and M. Kocheisen, “Multi-modal system for locating heads and faces,” in Proceedings of the Second International Conference on Automatic Face and Gesture Recognition, pp. 88-93, 1996.
[28] 廖偉全, 以電腦視覺為基礎之眼睛定位與追蹤技術於即時的眨眼偵測, 碩士學位論文, 國立台灣科技大學資訊工程系, 台北市, 2005.
[29] I. Pitas and A. N. Venetsanopoulos, “Morphological shape decomposition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, no. 1, 1990, pp. 38-45.
[30] H. Fujiyoshi and A. Lipton, “Real-time human motion analysis by image skeletonization,” in Proceedings of the Fourth IEEE Workshop on Application of Computer Vision, pp. 19-21, 1998.
[31] R. C. Gonzalez and R. E. Woods, Digital Image Processing, 2nd Ed., Addison-Wesley, Reading, Massachusetts, 1992.
[32] K. Suzuki, I. Horiba, N. Sugie, “Linear-time connected-component labeling based on sequential local operations,” Source Computer Vision and Image Understanding Archive, vol. 89 , no. 1, pp. 1-23, 2003.
[33] 宋炫慶, 基於粒子濾波技術的多個移動物體之即時視覺偵測與追蹤, 碩士學位論文, 國立台灣科技大學資訊工程系, 台北市, 2005.
[34] 景雅新, 光流技術在移動物體影像追尋上之應用, 碩士學位論文, 國立中山大學機械與機電工程學系, 高雄市, 2003.
[35] G. Welch and G. Bishop, “An Introduction to the Kalman Filter,” 2004.
[36] M. Montemerlo, S. Thrun, and W. Whittaker, “Conditional particle filters for simultaneous mobile robot localization and people-tracking,” in Proceedings of the IEEE International Conference on Robotics and Automation, vol. 1 , pp. 695-701, 2002.
[37] S. Caifeng, W. Yucheng, T. Tieniu, and O. Frederic, “Real time hand tracking by combining particle filtering and mean shift,” in Proceedings of the Sixth IEEE International Conference on Automatic Face and Gesture Recognition, pp. 669-674, 2004.
[38] K. Nummiaro, E. Koller-Meier, and L. Van Gool, “An adaptive color-based particle filter,” Image and Vision Computing, vol. 21, no. 1, pp. 99-110, 2003.
[39] M. Acharyya and M. K. Kundu, “Document image segmentation using wavelet scale-space features,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 12, no. 12, pp. 1117-1127, 2002.
[40] 黃伊正, 一個階段式的人臉辨識系統,碩士學位論文, 逢甲大學資訊工程學系, 台中市, 2003.
[41] Y. Freund and R. E. Schapire, “Experiments with a new boosting algorithm,” in Proceedings of the 13th International Conference on Machine Learning, pp. 148-156, 1996.
[42] J. Friedman, T. Hastie, and R. Tibshirani, “Additive logistic regression: a statistical view of boosting,” The Annals of Statistics, vol. 28, no. 2, pp. 337-407, 2000.
[43] R. E. Schapire and Y. Singer, “Improved boosting algorithms using confidence-rated predictions,” Machine Learning, vol. 37, no. 3, pp. 297-336, 1999.
[44] A. Vezhnevets, GML AdaBoost Matlab Toolbox, Graphics and Media Laboratory, Computer Science Department, Moscow State University, Moscow, Russian Federation, http://research.graphicon.ru/.
[45] L. Breiman, J. Friedman, R. Olshen, and C. Stone, Classification and Regression Trees, Chapman and Hall, New York, 1984.
[46] W. Zuo, D. Zhang, J. Yang, and K. Wang, “A novel fast feature extraction technique for face recognition,” IEEE Transactions on Systems, Man and Cybernetics– Part B: Cybernetics, vol. 36, no. 4, 2006.