臺灣博碩士論文加值系統

目前人臉識別技術已被廣泛利用於安全應用，如安全監控和門禁管制。但是人臉識別系統仍存在一些問題，其中以光線的變化，表情變化，頭部姿勢轉動與飾品遮蔽和人臉老化的影響是主要議題。對於老化的影響，形狀和紋理的變化會降低人臉識別系統的效能。我們的目標是提出一個強健的人臉老化呈現方式，因此，演算法主要在於研究如何模擬人臉圖像。
在這篇論文中，建立人臉圖像模型是一個重要的老化模擬過程。我們提出了一個老齡化的模擬方法。基於臉部肌肉模型，我們另外建立雙模模型，此方法可以從子空間的年齡群估算出最適合目標年齡人臉的形狀和紋理變化。最後應用PCA於人臉識別系統，將模擬的結果與真實的圖像做比較。實驗結果顯示，我們所提出的老化模擬方法可以提高人臉辨識系統的效能。

Recently, the techniques of face recognition have been widely used in security application such as security monitoring, and access control. However, there are still some problems in face recognition system which the light changes, expression changes, head movements, accessory occlusion and aging effect are the main issues. For the aging effect, the shape and texture change degrades the performance of face recognition system. Our goal is to come up with a representation that is robust to changes due to facial aging. Therefore, there are many algorithms focusing on how to simulate face image.
In this thesis, the modeling of face image is an important procedure for aging simulation. We propose an aging simulation scheme. Based on the facial muscle model, our scheme also applies bimode model which can estimate the geometric and texture variation of a target age from subspace of age groups. Finally, the PCA is applied to face recognition system. The simulating results presented in the thesis are compared with the ground truth image of the same person. Experimental results show that the proposed aging simulation scheme is able to improve performance of face recognition system.

Chapter 1 Introduction 1
1.1 Motivation 1
1.2 Thesis Organization 3

Chapter 2 Background 5
2.1 Face Modeling 5
2.2 Age Synthesis Algorithms 6

Chapter 3 Related Works 11
3.1 Muscle Modeling 11
3.1.1 Water's Model 11
3.1.2 Modeling the Muscle Model 12
3.2 Tensor Based Model 16
3.2.1 Tensorface Model 17
3.2.2 Bimode Model 18
3.3 Viola-Jones Object Detection 22

Chapter 4 The Proposed Scheme in Aging Simulation 25
4.1 Modeling the Facial Muscle 26
4.1.1 Parametric Muscle Model 26
4.1.2 Computing the Muscle Growth Parameter 29
4.1.3 Deformation of Facial Muscle 31
4.2 Bimode Model for Database Training 32
4.2.1 Image Preprocessing 32
4.2.2 Decomposing Training Data 35
4.2.3 Estimating the Person and Age Subspace 37
4.3 Face Recognition by PCA 38

Chapter 5 Experimental Results 39
5.1 FG-NET Aging Database 39
5.2 Experiments of Subjective Quality 42
5.3 Comparison with Other Methods 44
5.4 Experiments of Face Recognition 44

Chapter 6 Conclusion 47
Acknowledgement 49
References 49

[1] H. Ling, S. Soatto, N. Ramanathan, and D. Jacobs, “A Study of Face Recognition as People Age” Proc. IEEE Conf. Computer Vision, 2007.

[2] N. Ramanathana, R. Chellappa, and S. Biswas, “Computational Methods for Modeling Facial Aging: A Survey” J. Visual Languages and Computing, vol. 20, no. 3, pp. 131-144, 2009.

[3]Yun Fu; Guodong Guo; Huang, T.S.,“Age Synthesis and Estimation via Faces: A Survey” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.32, no.11, pp.1955-1976, Nov. 2010

[4] K. Ricanek, E. Boone, and E. Patterson, “Craniofacial Aging on the Eigenface Biometric” Proc. IASTED Int’l Conf. Visualization, Imaging, and Image Processing, pp. 249-253, 2006.

[5] S. Mukaida, H. Ando, K. Kinoshita, M. Kamachi, and K. Chihara, “Facial Image Synthesis Using Age Manipulation Based on Statistical Feature Extraction,” Proc. Conf. Visualization, Imaging, and Image Processing, 2002.

[6] N. Ramanathan and R. Chellappa, “Face Verification across Age Progression,” IEEE Trans. Image Processing, vol. 15, no. 11,pp. 3349-3361, Nov. 2006.

[7] L. Boissieux, G. Kiss, N.M. Thalmann, and P. Kalra, “Simulation of Skin Aging and Wrinkles with Cosmetics Insight,” Proc. Euro graphics Workshop Animation and Simulation, pp. 15-27, 2000.

[8] T. Kuratate and T. Nishita, “A Simple Method for Modeling Wrinkles on Human Skin,” Proc. Pacific Conf. Computer Graphics and Applications, pp. 166-175, 2002.

[9] T. Cootes, G. Edwards, and C. Taylor, “Active Appearance Models,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 6, pp. 681-685, June 2001.

[10] A. Lanitis, C. Taylor, and T. Cootes, “Toward Automatic Simulation of Aging Effects on Face Images,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, no. 4, pp. 442-455, Apr.2002.

[11] E. Patterson, A. Sethuram, M. Albert, and K. Ricanek, “Comparison of Synthetic Face Aging to Age Progression by Forensic Sketch Artist,” Proc. Seventh IASTED Int’l Conf. Visualization, Imaging, and Image Processing, pp. 247-252, 2007.

[12] N. Ramanathan and R. Chellappa, “Modeling Age Progression in Young Faces,” Proc. Int’l Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 387-394, 2006.

[13] A.C. Berg and S.C. Justo, “Aging of Orbicularis Muscle in Virtual Human Faces,” Proc. Seventh Int’l Conf. Information Visualization, pp. 164-168, July 2003.

[14] W.S. Lee, Y. Wu, and N.M. Thalmann, “Cloning and Aging in a VR Family,” Proc. Virtual Reality, pp. 61-68, Mar. 1999.

[15] L. Boissieux, G. Kiss, N.M. Thalmann, and P. Kalra, “Simulation of Skin Aging and Wrinkles with Cosmetics Insight,” Proc. Eurographics Workshop Animation Computer Animation and Simulation, pp. 15-27, 2000.

[16] J. Wang, Y. Shang, G. Su, and X. Lin, “Age Simulation for Face Recognition,” Proc. Int’l Conf. Pattern Recognition, pp. 913-916, 2006.

[17] Unsang Park; Yiying Tong; Jain, A.K. “Age-Invariant Face Recognition, ” IEEE Trans. Pattern Analysis and Machine Intelligence, vol.32, no.5, pp.947-954, May 2010.

[18] K. Ueki, T. Hayashida, and T. Kobayashi, “Subspace-Based Age-Group Classification Using Facial Images under Various Lighting Conditions,” Proc. IEEE Conf. Automatic Face and Gesture Recognition, pp. 43-48, 2006

[19] G. Guo, Y. Fu, T.S. Huang, and C. Dyer, “Locally Adjusted Robust Regression for Human Age Estimation,” Proc. IEEE Workshop Applications of Computer Vision, 2008.

[20] J. Suo, T. Wu, S.C. Zhu, S. Shan, X. Chen, and W. Gao, “Design Sparse Features for Age Estimation Using Hierarchical Face Model,” Proc. Eighth Int’l Conf. Automatic Face and Gesture Recognition, 2008.

[21] S. Rana, W. Liu, M. Lazarescu, S. Venkatesh, “Efficient tensor based face recognition,” 19th International Conference on Pattern Recognition. (2008) 1–4.

[22] S. Rana, W. Liu, M. Lazarescu, S. Venkatesh, “A unified tensor framework for face recognition,” Pattern Recognition 42 (2009) 2850–2862.

[23] H. Wang, N. Ahuja, “Facial expression decomposition,” Proceedings of the Ninth IEEE International Conference on Computer Vision, vol. 2,pp.958-965, Oct. 2003.

[24] Sung Won Park, Savvides, M., “Estimating Mixing Factors Simultaneously in Multilinear Tensor Decomposition for Robust Face Recognition and Synthesis,” Computer Vision and Pattern Recognition Workshop, 2006. CVPRW '06. Conference on , vol., no., pp. 49, 17-22 June 2006

[25] Y.C. Lee, D. Terzopoulos, and K. Waters, “Realistic Modeling for Facial Animation,” Proc. ACM SIGGRAPH, pp. 55-62, 1995.

[26] T.F. Cootes, D. Cooper, C.J. Taylor, and J. Graham, “Active Shape Models-Their Training and Application,” Computer Vision and Image Understanding, vol. 61, no. 1, pp. 38-59, Jan. 1995.

[27] T. Kuratate and T. Nishita, “A Simple Method for Modeling Wrinkles on Human Skin,” Proc. Pacific Conf. Computer Graphics and Applications, pp. 166-175, 2002.

[28] T. Cootes, G. Edwards, and C. Taylor, “Active Appearance Models,” Proc. European Conf. Computer Vision, vol. 2, pp. 484-498, 1998.

[29] Fangyuan Jiang, Yunhong Wang , “Facial aging simulation based on super-resolution in tensor space,” 15th IEEE International Conference on Image Processing, 2008. vol., no., pp.1648-1651, 12-15 Oct. 2008.

[30] Y. Fu and N. Zheng, “M-Face: An Appearance-Based Photorealistic Model for Multiple Facial Attributes Rendering,” IEEE Trans. Circuits and Systems for Video Technology, vol. 16, no. 7, pp. 830-842, July 2006.

[31] P.L. Williams, R. Warwick, M. Dyson, and L.H. Bannister, Gray’s Anatomy, 37th ed. London: Churchill Livingstone, 1989.

[32] K. Waters,“A Muscle Model for Animation Three-Dimensional Facial Expression,” Proc. ACM SIGGRAPH, pp. 17-24, 1987.

[33] N. Ramanathan and R. Chellappa, “Modeling Shape and Textural Variations in Aging Faces,” Proc. IEEE Conf. Series on Automatic Face and Gesture Recognition, 2008.

[34] M. A. O. Vasilescu and D. Terzopoulos, “Multilinear analysis of imageensembles: Tensorfaces,” in Proc. 7th Eur. Conf. Comput. Vis., May 2002, pp. 447–460.

[35] Hui Yan, Jian Yang, Jingyu Yang, “ Bimode model for face recognition and face representation ” Neurocomputing, Vol. 74, Issue 5, pp. 741-748, Feb. 2011.

[36] P. Viola and M. Jones, “Robust real-time face detection.” Proceeding of Fighth International Conference on Computer Vison, Vancouver, Vol.20(11), 2001, pp. 1254-1259.

[37] C.Papageorgiou, M. Oren, and T. Poggio, “Ageneral framework for object detection.” International Conference on Computer Vision. 1998.

[38] B.W. Bader, T.G. Kolda Tensor toolbox version 2.2. Available at: http://csmr.ca.sandia.gov/~tgkolda/TensorToolbox/
[39] M. Turk, and A. Pentland, “Eigenfaces for Recognition,” Journal of Cognitive Neuroscience, vol.3, no.1, pp.71-86, 1991.
[40] FG-Net Aging Database, [Online]. Available: http://www.fgnet.rsunit.com

[41] S. Milborrow Stasm: locating facial features with ASM. Available: http://www.milbo.users.sonic.net/

[42] T. Cootes: am_tools. Available: http://personalpages.manchester.ac.uk/staff/ timothy.f.cootes/