臺灣博碩士論文加值系統

近年來，由於「智慧生活」科技的提倡，人臉辨識技術已延伸至人與機器最佳化介面的實現，使得人臉辨識系統廣泛地應用於身份辨識、門禁監控與人機介面等領域；有鑑於此，我們在本論文中提出一個具有即時自動多重人臉辨識與追蹤功能的機器人跟隨系統，主要包括人臉偵測、人臉辨識與人臉追蹤三大程序。
在人臉偵測方面，我們使用AdaBoost分類器進行訓練，並利用一種階層結構來實行偵測；在人臉辨識程序，我們以二維哈爾小波轉換(two-dimensional Haar wavelet transform)取出人臉影像的低頻部份，而在人臉辨識的議題上，我們修改有辨別力的共通向量(discriminative common vectors)的演算法，來建立具有鑑別性的人臉特徵參數模型。最後，我們採用最小歐幾里德距離的決策方式，連續擷取10張人臉影像予以辨識後，投票判斷最有可能的人，並將其辨識結果分成兩大類：主人與陌生人，而機器人會以主人為主要目標進行追蹤；在確定目標物的類別後，進入人臉追蹤程序，於此，我們利用兩階段的粒子濾除器(particle filter)技術來動態追蹤多重人臉。根據人臉在畫面中的位置，對機器人的輪控馬達下達前進、左轉、右轉等指令，並且利用雷射測距儀，來判斷機器人與目標物的距離，進而下達停止或後退的指令，直到機器人跟隨目標物至一個適當的距離。
由實驗結果顯示，我們所提方法的人臉追蹤率在一般的情況下超過 97%，而在人臉產生交錯時的追蹤率可高於 82%，又人臉的辨識率經過統計得知，在一般的情況下，至少達到 93%；此外，對於機器人的整體系統執行效能可達到每秒處理 7 個畫面的速度。這樣的系統效能令人非常滿意並鼓舞我們將此機器人進一步商品化。

More recently, the technique of face recognition has been markedly extended to realize the optimality of human-computer interfaces due to the promotion of “intelligent life.” Face recognition has been broadly applied in many areas, such as biometric identity authentication, entrance guard, and human-computer interface in recent years. In view of the above-mentioned facts, a completely automatic real-time multi-faces recognition and tracking system installed on a person following robot is presented in this thesis, including face detection, face recognition, and face tracking procedures.
As to face detection, the AdaBoost technique is used in our system, and a structure of cascaded classifiers is adopted to detect human faces; in the face recognition procedure, we have captured face images and apply the two-dimensional Haar wavelet transform (2D-HWT) to acquire the low-frequency data of face images. We modify the discriminative common vectors (DCV) algorithm to setup the discriminative models of face features received from different persons. Finally, we utilize the minimum Euclidean distance to measure the similarity of the face image and a candidate person, and decide the most likely person by the majority voting of ten successive recognition results from a face image sequence. Subsequently, the results of recognition will be grouped into two classes: “master” and “stranger.” In our system, the robot will track the master unceasingly; after check the class of targets, our system will go to the face tracking procedure. Herein, we employ a two-level improved particle filter to dynamically locate multiple human faces. According to the position of the human face in an image, we issue a series of commands (moving forward, turning left or turning right) to drive the motors of wheels on a robot, and judge the distance between the robot and a person with the aid of a laser range finder to issue a set of commands (stop or turn backward) until the robot follows to a suitable distance in front of the person.
Experimental results reveal that the face tracking rate is more than 97% in general situations and exceeds 82% when the face occlusion happening. As for the face recognition, the correct rate is over 93% in general situations; besides this, the efficiency of system execution attains 7 frames per second at least in our system. Such system performance is very satisfactory and we are encouraged to commercialize the robot.

致謝 i
中文摘要 ii
Abstract iii
Contents v
List of Figures vii
List of Tables ix
Chapter 1 Introduction 1
1.1 Overview 1
1.2 Background and motivation 1
1.3 Our proposed methods 2
1.4 System description 3
1.5 Thesis organization and system architecture 5
Chapter 2 Related Works 7
2.1 Reviews of face detection 7
2.2 Reviews of face recognition 9
2.3 Reviews of face tracking 11
Chapter 3 Face Detection 13
3.1 Integral images 14
3.2 Rectangle features 15
3.3 AdaBoost techniques 18
3.4 Cascade classifiers 23
Chapter 4 Face Recognition 26
4.1 Preliminary processing 27
4.2 Wavelet transformation 27
4.3 Discriminative common vectors 31
4.4 Similarity measurement 37
Chapter 5 Face Tracking 39
5.1 The particle filter 40
5.2 Our face tracking method 46
5.2.1 Object representation 46
5.2.2 Similarity measurement of features 47
5.2.3 Particle filtering 48
5.2.4 Occlusion handling 53
5.2.5 Robot control 55
Chapter 6 Experimental Results 58
6.1 System interface description 59
6.2 The results of face detection 60
6.3 The results of face recognition 62
6.3.1 Face databases for discriminative common vectors 62
6.3.2 Experiments on the robot 64
6.3 The results of face tracking 67
Chapter 7 Conclusions and Future Works 71
7.1 Conclusions 71
7.2 Future works 72
References 74

[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, Mantova, Italy, pp.115-120, 2003.
[2]H. Zhao and R. Shibasaki, “A Real-Time System for Monitoring Pedestrians,” Application of Computer Vision, CO, USA, vol. 1, pp. 378-385, 2005
[3]P. Viola, and M. Jones, “Rapid object detection using a boosted cascade of simple features”. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Hawaii, USA, Vol. 1, pp. 511-518, 2001.
[4]W.S. Lee, H.J. Lee, and J.H. Chung, “Wavelet-based FLD for face recognition,” in Proceedings of the IEEE Midwest Symposium on Circuits and Systems, MI, USA, pp. 734-737, 2000.
[5]H. Cevikalp, M. Neamtu, M. Wilkes, and A. Barkana, “Discriminative common vectors for face recognition”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol 27, pp. 4-13, 2005.
[6]H. Cevikalp and M. Wilkes, “Face recognition by using discriminative common vectors,” in Proceedings of the International Conference on Pattern Recognition, Cambirdge, UK, Vol. 1, pp. 326-329, 2004.
[7]M.B. Gulmezoglu, V. Dzhafarov, and A. Barkana, “The common vector approach and its relation to principal component analysis,” IEEE Transactions on Speech and Audio Processing, vol. 9, no. 6, 2001.
[8]K. Y. Wang, “A real-time face tracking and recognition system based on particle filtering and AdaBoosting techniques,” Master Thesis, Department of Computer Science Information Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan, 2006.
[9]E. Hjelmås, and B. K. Low, “Face detection: a survey,” Computer Vision and Image Understanding, vol. 83, pp. 236-274, 2001.
[10]H. Lu and W. Shi, “Accurate active shape model for face alignment,” in Proceedings of the 17th IEEE International Conference on Tools with Artificial Intelligence, Hong Kong, China, vol. 13, pp. 1119-1128, 2005.
[11]S. H. Jeng, H. Y. M. Liao, C. C. Han, M. Y. Chern, and Y. T. Liu, “Facial feature detection using geometrical face model: an efficient approach,” Pattern Recognition, vol. 31, pp.273-282, 1998.
[12]M. Soriano, S. Huovinen, B. Martinkauppi, and M. Laaksonen, “Using the skin locus to cope with changing illumination conditions in color-based face tracking,” in Proceedings of the IEEE Nordic Signal Processing Symposium, Kolmarden, Sweden, pp. 383-386, 2000.
[13]R. C. Gonzalez and R. E. Woods, Digital Image Processing, 2nd Ed., Addison-Wesley, Reading, Massachusetts, 1992.
[14]S. L. Phung, A. Bouzerdoum, and D. Chai, “A novel skin color model in YCbCr color space and its application to human face detection,” in Proceedings of IEEE International Conference on Image Processing, New York, USA, vol. 1, pp. 289-291, 2002.
[15]M. H. Yang, N. Ahuja, and D. Kriegman, “Face detection using mixtures of linear subspaces,” in Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition, Grenoble, France, pp. 70-76, 2000.
[16]A. M. Martinez and A. C. Kak, “PCA versus LDA,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, pp. 228-233, 2001.
[17]C. Y. Chang and S. Y. Fu, “Image classification using a module RBF neural network,” in Proceedings of the First International Conference on Innovative Computing, Information and Control, Beijing, China, vol. 2, pp. 270-273, 2006.
[18]C. A. Waring and X. Liu, “Face detection using spectral histograms and SVMs,” IEEE Transactions on System, vol. 35, pp. 467- 476, 2005.
[19]W. Zhao, R. Chellappa, P. J. Phillips, and A. Rosenfeld, “Face recognition: a literature survey,” ACM Computing Surveys, vol. 35, no. 4, pp. 399-458, 2003.
[20]S. Z. Li and J. Lu, “Face recognition using the nearest feature line method,” IEEE Transactions on Neural Networks, vol. 10, pp. 439-443, 1999.
[21]R. Brunelli and T. Poggio, “Face recognition: features versus templates,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.15, pp. 1042, 1993.
[22]M. J. Er, S. Wu, J. Lu, and H. L. Toh, “Face recognition with radial basis function (RBF) neural networks,” IEEE Transactions on Neural Networks, vol. 13, pp. 697-710, 2002.
[23]Y. Nara, J. Yang, and Y. Suematsu, “Face recognition using improved principal component analysis,” in Proceedings of the International Symposium on Micromechatronics and Human Science, pp. 77 - 82, 2003.
[24]K. C. Fan, Y. K. Wang, and B. F. Chen, “Introduction of tracking algorithms,” Image and Recognition, Vol. 8, No. 4, pp. 17-30, 2002.
[25]K. H. An, D. H. Yoo, S. U. Jung, and M. J. Chung, “Robust multi-view face tracking,” in Proceedings of the IEEE International Conference on Intelligent Robots and Systems, Alberta, Canada, pp. 1905-1910, 2005.
[26]R. Lienhart, A. Kuranov, and V. Pisarevsky, “Empirical analysis of detection cascades of boosted classifiers for rapid object detection”. DAGM’ 03 25th Pattern Recognition Symposium, Magdeburg, Germany, 2003.
[27]Z. Q. Zhang, L. Zhu, S. Z. Li, and H. J. Zhang, “Real-time multi-view face detection”. Automatic Face and Gesture Recognition Proceeding, Fifth IEEE International Conference, New York, USA, pp.140-147, 2002.
[28]C. Liu and H. Wechsler, “Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition,” IEEE Transactions on Image Processing, vol.11, pp.467- 476, 2002.
[29]M. Turk and A. Pentland, “Face recognition using eigenfaces,＂in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Hawaii, USA, pp. 586-591, 1991.
[30]Y. Bing, J. Lianfu, and C. Ping, “A new LDA-based method for face recognition,” in Proceedings of the International Conference Pattern Recognition, Quebec, Canada, vol. 1, pp. 168-171, 2002
[31]R. Huang, Q. Liu, H. Lu, and S. Ma, “Solving the small size problem of LDA,” in Proceedings of the International Conference on Pattern Recognition, Quebec, Canada, vol. 3, pp. 29-32, 2002.
[32]L. F. Chen, H. Y. M. Liao, M. T. Ko, J. C. Lin, and G. J. Yu, “A new LDA-based face recognition system which can solve the small sample size problem,” in Proceedings of the International Conference on Pattern Recognition, Barcelona, Spain, vol. 33, pp. 1713-1726, 2000.
[33]Y. H. Ching, “Visual tracking for a moving object using optical flow technique,” Master Thesis, Department of Mechanical and Electro- Mechanical Engineering, National Sun Yat Sen University, Kaohsiung, 2003.
[34]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, Washington, USA, vol. 1, pp. 695-701, 2002.
[35]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.