臺灣博碩士論文加值系統

近年來，人與機器人互動成為機器人學及相關領域中熱烈討論的一個重要課題。由於人臉可能是人類最富有表現自己想法的部位，因此，觀察人臉成為了人與機器人互動中最重要的任務之一。過去二十年，主動外觀模型（Active Appearance Model）成功地建立了人臉模型並且能在影像中找到人臉細部特徵的位置，如眼睛、鼻子和嘴巴。主動外觀模型可成為分析與瞭解人類表情的重要工具之一。但現有主動外觀模型利用平面形狀模型來為立體的人臉建模，其中立體的資訊就被忽略了。因此，當像機拍攝到非正臉的人臉時，就有極高可能無法正確地找到這些特徵。在此篇論文中，我們提出三維立體主動外觀模型來克服此問題。我們所提出之三維立體主動外觀模型包含了一立體形狀模型（3D Shape Model）以及外觀模型（Appearance Model）。此模型於訓練階段時僅需要正臉的人臉資料即可。即使在有轉動姿勢的人臉的情況下，也可成功地定位人臉的細部特徵。經由20個人的資料庫所訓練並測試的實驗結果顯示出所提出的演算法的成功辨識率更可達80%。

Perceiving human faces is one of the most important functions for human robot interaction. The active appearance model (AAM) is a statistical approach that models the shape and texture of a target object. According to a number of the existing works, AAM has a great success in modeling human faces. Unfortunately, the traditional AAM framework could fail when the face pose changes as only 2D information is used to model a 3D object. To overcome this limitation, we propose a 3D AAM framework in which a 3D shape model and an appearance model are used to model human faces. Instead of choosing a proper weighting constant to balance the contributions from appearance similarity and the constraint on consistent 2D shape with 3D shape in the existing work, our approach directly matches 2D visual faces with the 3D shape model. No balancing weighting between 2D shape and 3D shape is needed. In addition, only frontal faces are needed for training and non-frontal faces can be aligned successfully. The experimental results with 20 subjects demonstrate the effectiveness of the proposed approach.

ABSTRACT ii
LIST OF FIGURES v
LIST OF TABLES vi
CHAPTER 1. Introduction 1
CHAPTER 2. Related Works 3
CHAPTER 3. 2D Active Appearance Model 5
3.1. 2D Shape Model 5
3.2. Appearance Model 6
3.3. Pose Variations 7
3.4. Texture Transformation between Two Shapes 7
3.5. Fitting an AAM to an Image 8
CHAPTER 4. 3D Active Appearance Model 10
4.1. 3D Active Appearance Model 10
4.1.1. 3D Shape Model 10
4.1.2. Mapping from 3D Shape to 2D Shape 11
4.1.3. Texture Transformation between Two Shapes 11
4.2. Fitting an 3D AAM to an Image 12
4.2.1. Linearization of the Cost Function 13
4.2.2. Minimization of the Cost Function 13
4.2.3. Warp Jacobian 14
CHAPTER 5. Experimental Results 17
5.1. Data Collection 17
5.2. Software and Hardware 19
5.3. Experiments 19
5.4. Results 20
5.4.1. The Person-Specific Case 20
5.4.2. The Multi-Person Case 21
5.4.3. Glasses 22
5.4.4. 3D Pose Variations 22
5.5. Computational Complexity 22
CHAPTER 6. Conclusions and Future Works 33
6.1. Conclusions 33
6.2. Future Works 33
BIBLIOGRAPHY 34

Baker, S. & Matthews, I. (2001). Equivalence and efficiency of image alignment algorithms. Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on, 1, I–1090–I–1097 vol.1.

Baker, S. & Matthews, I. (2004). Lucas-kanade 20 years on: A unifying framework. International Journal of Computer Vision, 56(3), 221 – 255.

Blanz, V. & Vetter, T. (1999). A morphable model for the synthesis of 3d faces. In SIGGRAPH’99: Proceedings of the 26th annual conference on Computer graphics and interactive techniques,(pp. 187–194)., New York, NY, USA. ACM Press/Addison-Wesley Publishing Co.

Cootes, T. (2003). Timeline of developments in asms and aams.

Cootes, T. & Taylor, C. (1992). Active shape models- - smart snakes. British Machine Vision Conference.

Cootes, T. & Taylor, C. (1994). Modelling object appearance using the greylevel surface. In Proceedings of the British Machine Vision Conference.

Cootes, T. & Taylor, C. (2001). Constrained active appearance models. Computer Vision, 2001. ICCV 2001. Proceedings. Eighth IEEE International Conference on, 1, 748–754 vol.1.

Cootes, T.,Walker, K., & Taylor, C. (2000). View-based active appearance models. Automatic Face and Gesture Recognition, 2000. Proceedings. Fourth IEEE International Conference on,
227–232.

Cootes, T. F., Cooper, D. H., Taylor, C. J., & Graham., J. (1991). A trainable method of parametric shape description. British Machine Vison Conference, 54–61.

Cootes, T. F., Cooper, D. H., Taylor, C. J., & Graham, J. (1992). Trainable method of parametric shape description. Image Vision Comput., 10(5), 289–294.

Cootes, T. F., Edwards, G. J., & Taylor, C. J. (2001). Active appearance models. IEEE Trans. Pattern Anal. Mach. Intell., 23(6), 681–685.

Edwards, G., Taylor, C., & Cootes, T. (14-16 Apr 1998). Interpreting face images using active appearance models.

Automatic Face and Gesture Recognition, 1998. Proceedings. Third IEEE International Conference on, 300–305.

Englebienne, G., Cootes, T. F., & Rattray, M. (2008). A probabilistic model for generating realistic lip movements from speech. In Neural Information Processing Systems.

Goodall, C. (1991). Procrustes methods in the statistical analysis of shape. Journal of the Royal Statistical Society. Series B (Methodological), 53(2), 285–339.

Gross, R., Matthews, I., & Baker, S. (2006). Active appearance models with occlusion. Image and Vision Computing, 24(6), 593–604.

Hu, C., Xiao, J., Matthews, I., Baker, S., Cohn, J., & Kanade, T. (2004). Fitting a single active appearance model simultaneously to multiple images. In Proceedings of the British Machine Vision Conference.

Koterba, S. C., Baker, S., Matthews, I., Hu, C., Xiao, J., Cohn, J., & Kanade, T. (2005). Multiview aam fitting and camera calibration. In Proc. International Conference on Computer Vision, volume 1, (pp. 511 – 518).

Lanitis, A., Taylor, C., & Cootes, T. (15 Sep 1994a). Automatic tracking, coding and reconstruction of human faces, using flexible appearance models. Electronics Letters, 0(19), 1587–1588.

Lanitis, A., Taylor, C. J., & Cootes, T. F. (1994b).
Automatic tracking, coding and reconstruction of human faces using flexible appearance models. IEEE Electronic Letters, 30, 1578–1579.

Matthews, I. & Baker, S. (2004). Active appearance models revisited. International Journal of Computer Vision, 60(2), 135 – 164.

Pentland, A., Moghaddam, B., & Starner, T. (1994). View-based and modular eigenspaces for face recognition. in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 84–91.

Stegmann, M. B. (2003). The AAM-API: An open source active appearance model implementation. In Medical Image Computing and Computer-Assisted Intervention - MICCAI 2003, 6th Int. Conference, Montr′eal, Canada, LNCS 2879, (pp. 951–952). Springer.

Viola, P. & Jones, M. (2001). Robust real-time face detection. Computer Vision, 2001. ICCV
2001. Proceedings. Eighth IEEE International Conference on, 2, 747–747.

Xiao, J., Baker, S., Matthews, I., & Kanade, T. (2004). Real-time combined 2d+3d active appearance models. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, volume 2, (pp. 535 – 542).

Zhao,W., Chellappa, R., Phillips, P. J., & Rosenfeld, A. (2003). Face recognition: A literature survey. ACM Comput. Surv., 35(4), 399–458.