臺灣博碩士論文加值系統

在大多數有關自動化的頭部偵測與追蹤、人臉辨識等等的應用多少都會受到光影環境不同的影響，使得效果不盡理想。尤其是在虛擬視訊會議系統當中，精確地表情分析更是受到光影環境的影響。於是，我們希望能在不同的光影環境下依舊可以快速地選出可能的人臉區塊，並且補償光影的影響效果，以進一步判別人臉的出現與否。而頭部姿勢估測是整個流程中最花費時間的運算。因此，我們會嘗試著減少頭部姿勢估測所耗費的時間。
首先，我們採用一個膚色模型，它包含了在不同光影環境下的訓練資料。因此可以在大部分的光影環境下，正確地選出屬於膚色的像素。然而，更重要的是如何調整膚色模型以符合當前的光影條件。接著我們並不直接對目前的影像做全面性地掃瞄，取而代之的是掃瞄降低取樣後的膚色圖（skin map）以及應用膚色的遮罩來加快篩選可能包含人臉的區塊。再來，我們修改算數平均數平移法（mean shift algorithm）來微調掃瞄的區域與膚色遮罩以增加精確度與提高速度。對於可能包含人臉的膚色區塊，我們採用二次方程式來估測光影的分佈，進而去除光影的影響。支援向量機（support vector machine）可以很好地應用在判別人臉的出現與否。最後，我們修改一個自動選取好的特徵點的演算法，並套用在材質圖（texture map）上以自動選取包含二個方向性邊緣（edge）的特徵點來進行頭部姿勢的估測，以減少頭部所耗費的時間。

Most of the facial animation applications, such as automatic face detection, recognition, and tracking are sensitive to the different lighting conditions and worse background environment, especially accurate expression analysis in virtual conferencing system. The main work in our system is to detect the face under these complex situations and reduce the influence of different lighting. In addition, the pose estimation is the bottleneck of the framework, the speed of which is to be improved.
First, we adopt a skin color model, which includes the training data under different lighting conditions, and the pixels which belong to skin color are detected correctly in most situations. Instead of overall scanning the original image, we scan the down-sampled skin map and apply the skin mask to obtain the possible facial blocks fast. Further, a modified mean shift algorithm is used to refine the accuracy of overall scanning and skin mask and also improve the speed by increasing the step size of scanning. The lighting distribution is estimated by second order function, and the lighting effect is compensated. After lighting compensation, we introduce the support vector machine classification to check if a block includes face or not, and it is easier to classify the blocks of face or non-face in the candidates of the subset of skin color. Finally, we modify the good features selection algorithm to the texture map to pick out the features which contain the edges of two different directions, and then perform the analysis-by-synthesis pose estimation with the texture map of good features to speed up without losing accuracy.

Chapter 1: Introduction 1
1.1 Virtual Conferencing 1
1.2 Overview of Out Work 1
1.3 Related Work 2
1.4 Thesis Organization 3
Chapter 2: Framework and System Overview 4
2.1 Framework Overview 4
2.2 System Overview 7
Chapter 3: Head Tracking under Different Lighting Conditions 11
3.1 Head Tracking Overview 12
3.2 Adaptive Skin Color Model 14
3.2.1 Skin Color Model 15
3.2.2 Adaptability of Skin Color Model 19
3.3 Overall Scanning and Skin Mask 30
3.3.1 Overall Scanning 30
3.3.2 Skin Mask 32
3.4 Fine Tuning with Mean Shift Algorithm 35
3.4.1 Mean Shift Algorithm 35
3.4.2 Fine Tuning Algorithm 36
3.5 Lighting Compensation and Normalization 39
3.5.1 Lighting Estimation 41
3.5.2 Normalization 42
3.6 Summary and Discussion 43
Chapter 4: Face Verification and Pose Estimation 44
4.1 Pose Estimation 44
4.2 FAP Mapping 46
4.3 Support Vector Machine 47
4.3.1 Support Vector Machine Theory 48
4.3.2 Face Verification 55
4.4 Faster Pose Estimation 57
4.5 Summary and Discussion 62
Chapter 5: Conclusion and Future Work 63

[1] J. Shi and C. Tomasi,
"Good Features to Track,"
National Science Foundation under contract IRI-9201751, Dec. 1993.
[2] H. Wang and S.-F. Chang,
"A highly efficient system for automatic face region detection in MPEG video,"
IEEE Trans. Circuits System Video Technology, vol. 7, no. 4, pp. 615-628, Aug. 1997.
[3] K.-K. Sung and T. Poggio,
"Example-Based Learning for View-Based Human Face Detection,"
IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 20, no. 1, pp. 39-51, Jan. 1998.
[4] H. A. Rowley, S. Baluja, and T. Kanade,
"Neural Network-Based Face Detection",
IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 20, no. 1, pp. 23-38, Jan. 1998.
[5] S. Haykin,
"Neural Networks - A Comprehensive Foundation,"
2nd Ed., Prentice-Hall, 1999.
[6] C. Garcia and G. Tziritas,
"Face Detection Using Quantized Skin Color Regions Merging and Wavelet Packet Analysis,"
IEEE Trans. on Multimedia, vol. 1, no. 3, pp. 264-277, Sept. 1999.
[7] D. Comaniciu and P. Meer,
"Mean Shift Analysis and Applications,"
Proc. 7th Int'l Conf. Computer Vision, pp. 1197-1203, Sept. 1999.
[8] J. C. Chou,
"Feature Point Tracking of Human Face and Facial Expression Analysis,"
國立清華大學碩士論文, Jun. 2000.
[9] Y. Li, S. Gong and H. Liddell,
"Support Vector Regression and Classification Based Multi-view Face Detection and Recognition,"
IEEE International Conference on Automatic Face and Gesture Recognition, 2000.
[10] Y. J. Chang and Y. C. Chen,
"Robust Head Pose Estimation Using Textured Polygonal Model with Local Correlation Measure,"
Proceedings of the 2nd IEEE Pacific-Rim Conference on Multimedia. Beijing, China, pp. 245-252, Oct. 2001.
[11] P. Viola and M. Jones,
"Robust Real-time Object Detection",
2nd International Workshop on Statistical and Computational Theories of Vision - Modeling, Learning, Computing, and Sampling. Vancouver, Canada, Jul. 2001.
[12] S. Z. Li, X. G. Lv, H. J. Zhang.
"View-Based Clustering of Object Appearances Based on Independent Subspace Analysis,"
Proceedings of 8th IEEE International Conference on Computer Vision. Vancouver, Canada, Jul. 2001.
[13] Y. J. Chang,
"Analysis and Synthesis if Facial Expressions for Virtual Conferencing Systems,"
國立清華大學博士論文, Jul. 2002.
[14] C. C. Chien,
"Facial Expression Analysis under Various Head Post,"
國立清華大學碩士論文, Jun. 2002.
[15] Y. J. Chang and Y. C. Chen,
"Facial Model Adaptation from a Monocular Image Sequence using a Textured Polygonal Model,"
Signal Processing: Image Communication, vol. 17, no. 5, pp. 373-392, May 2002.
[16] S. B. Gokturk, J.-Y. Bouguet, C. Tomasi, and B. Girod,
"Model-Based Face Tracking for View-Independent Facial Expression Recognition,"
Proceedings of the 5th IEEE International Conference on Automatic Face and Gesture Recognition, 2002.
[17] S. Z. Li, X. H. Peng, H. J. Zhang, Q. S. Cheng.
"Multi-View Face Pose Estimation Based on Supervised ISA Learning,"
Proceedings of the 5th International Conference on Automatic Face and Gesture Recognition. Washington, DC, USA. May, 2002.
[18] Z. Q. Zhang, L. Zhu, A. Z. Li, and H. J. Zhang,
"Real-Time Multi-view Face Detection",
Proceedings of the 5th International Conference on Automatic Face and Gesture Recognition. Washington DC, USA, vol. 1, pp.207-212. May, 2002.
[19] D. Comaniciu, V. Ramesh, and P. Meer,
"Kernel-Based Object Tracking,"
IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 25, no. 5, pp. 564-577, May 2003.