The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.06 - June (2009 vol.31)
pp: 1102-1116
Hyung-Soo Lee , Pohang University of Science and Technology, Pohang
Daijin Kim , Pohang University of Science and Technology, Pohang
ABSTRACT
The Active appearance model (AAM) is a well-known model that can represent a non-rigid object effectively. However, the fitting result is often unsatisfactory when an input image deviates from the training images due to its fixed shape and appearance model. To obtain more robust AAM fitting, we propose a tensor-based AAM that can handle a variety of subjects, poses, expressions, and illuminations in the tensor algebra framework, which consists of an image tensor and a model tensor. The image tensor estimates image variations such as pose, expression, and illumination of the input image using two different variation estimation techniques: discrete and continuous variation estimation. The model tensor generates variation-specific AAM basis vectors from the estimated image variations, which leads to more accurate fitting results. To validate the usefulness of the tensor-based AAM, we performed variation-robust face recognition using the tensor-based AAM fitting results. To do, we propose indirect AAM feature transformation. Experimental results show that tensor-based AAM with continuous variation estimation outperforms that with discrete variation estimation and conventional AAM in terms of the average fitting error and the face recognition rate.
INDEX TERMS
Tensor Algebra, Multilinear Analysis, Active Appearance Model, Least Square Estimation, Indirect AAM Feature Transformation, Vriation-Robust Face Recognition
CITATION
Hyung-Soo Lee, Daijin Kim, "Tensor-Based AAM with Continuous Variation Estimation: Application to Variation-Robust Face Recognition", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.31, no. 6, pp. 1102-1116, June 2009, doi:10.1109/TPAMI.2008.286
REFERENCES
[1] T. Cootes, G. Edwards, and C. Taylor, “Active Appearance Models,” Proc. European Conf. Computer Vision, pp.484-498, 1998.
[2] T.F. Cootes, G.J. Edwards, and C.J. Taylor, “Active Appearance Models,” IEEE Trans. Pattern Recognition and Machine Intelligence, vol. 23, no. 6, pp.681-685, June 2001.
[3] R. Beichel, S. Mitchell, E. Sorantin, F. Leberl, A. Goshtasby, and M. Sonka, “Shape- and Appearance-Based Segmentation of Volumetric Medical Images,” Proc. Int'l. Conf. Image Processing, pp.589-592, 2001.
[4] M.B. Stegmann, B.K. Ersbϕll, and R. Larsen, “Fame—A Flexible Appearance Modeling Environment,” IEEE Trans. Medical Imaging, vol. 22, no. 10, pp.1319-1331, 2003.
[5] G.J. Edwards, T.F. Cootes, and C.J. Taylor, “Face Recognition Using Active Appearance Models,” Proc. European Conf. Computer Vision, pp.581-595, 1998.
[6] T.F. Cootes, K. Walker, and C.J. Taylor, “View-Based Active Appearance Models,” Proc. Fourth IEEE Int'l Conf. Automatic Face and Gesture Recognition. p.227, 2000.
[7] S. Yan, X. Hou, S. Li, H. Zhang, and Q. Cheng, “Face Alignment Using View-Based Direct Appearance Models,” Int'l J. Imaging Systems and Technology, vol. 13, no. 1, pp.106-112, 2003.
[8] J. Sung and D. Kim, “A Real-Time Facial Expression Recognition Using the STAAM,” Proc. Int'l Conf. Pattern Recognition, 2006.
[9] B. Abboud and F. Davoine, “Face Appearance Factorization for Expression Analysis and Synthesis,” Proc. Workshop Image Analysis for Multimedia Interactive Services, 2004.
[10] H.-S. Lee and D. Kim, “Expression-Invariant Face Recognition by Facial Expression Transformations,” Pattern Recognition Letters, vol. 29, no. 13, pp.1797-1805, 2008.
[11] R. Donner, M. Reiter, G. Langs, P. Peloschek, and H. Bischof, “Fast Active Appearance Model Search Using Canonical Correlation Analysis,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 28, no. 10, pp.1690-1694, Oct. 2006.
[12] I. Matthews and S. Baker, “Active Appearance Models Revisited,” Int'l J. Computer Vision, vol. 60, no. 2, pp.135-164, Nov. 2004.
[13] J. Sung and D. Kim, “STAAM: Fitting a 2d+3d AAM to Stereo Images,” Proc. Int'l Conf. Image Processing, pp.2781-2784, 2006.
[14] S. Lee, J. Sung, and D. Kim, “Incremental Update of Linear Appearance Models and its Application to AAM: Incremental AAM,” Proc. Int'l Conf. Image Analysis and Recognition, pp.538-547, 2007.
[15] H.-S. Lee, J. Sung, and D. Kim, “Incremental AAM Using Synthesized illumination Images,” Proc. Pacific-Rim Conf. Multimedia, pp.675-684, 2007.
[16] S. Yan, C. Liu, S.Z. Li, H. Zhang, H.-Y. Shum, and Q. Cheng, “Texture-Constrained Active Shape Models,” Proc. Int'l Workshop Generative-Model-Based Vision, 2002.
[17] J. Sung, T. Kanade, and D. Kim, “A Unified Gradient-Based Approach for Combining ASM into AAM,” Int'l J. Computer Vision, vol. 75, no. 2, pp.297-309, 2007.
[18] C.M. Christoudias and T. Darrell, “Light Field Appearance Manifolds,” Proc. European Conf. Computer Vision, pp.481-493, 2004.
[19] C.M. Christoudias, L.-P. Morency, and T. Darrell, “Non-Parametric and Light-Field Deformable Models,” Computer Vision and Image Understanding, vol. 104, no. 1, pp.16-35, 2006.
[20] C.M. Christoudias and T. Darrell, “On Modelling Nonlinear Shape-and-Texture Appearance Manifolds,” Proc. IEEE Int'l Conf. Computer Vision and Pattern Recognition, pp.1067-1074, 2005.
[21] T.F. Cootes and C.J. Taylor, “On Representing Edge Structure for Model Matching,” Proc. IEEE Int'l Conf. Computer Vision and Pattern Recognition, pp.1114-1119, 2001.
[22] I.M. Scott, T.F. Cootes, and C.J. Taylor, “Improving Appearance Model Matching Using Local Image Structure,” Proc. Information Processing in Medical Imaging, pp.258-269, 2003.
[23] L. Xiaoming, “Generic Face Alignment Using Boosted Appearance Model,” Proc. IEEE Int'l Conf. Computer Vision and Pattern Recognition, pp.1-8, 2007.
[24] R. Gross, I. Matthews, and S. Baker, “Generic vs. Person Specific Active Appearance Models,” Image and Vision Computing, vol. 23, no. 11, pp.1080-1093, Nov. 2005.
[25] S. Lucey, I. Matthews, C. Hu, Z. Ambadar, F. De la Torre Frade, and J. Cohn, “AAM Derived Face Representations for Robust Facial Action Recognition,” Proc. Seventh IEEE Int'l Conf. Automatic Face and Gesture Recognition, pp.155-160, 2006.
[26] L. de Lathauwer, B. de Moor, and J. Vandewalle, “A Multilinear Singular Value Decomposition,” SIAM J. Matrix Analysis and Applications, vol. 21, no. 4, pp.1253-1278, 2000.
[27] M. Vasilescu and D. Terzopoulos, “Multilinear Analysis of Image Ensembles: Tensorfaces,” Proc. European Conf. Computer Vision, pp.447-460, 2002.
[28] M. Vasilescu and D. Terzopoulos, “Multilinear Analysis for Facial Image Recognition,” Proc. Int'l Conf. Pattern Recognition, 2002.
[29] H.-S. Lee and D. Kim, “Tensor-Based Active Appearance Model,” IEEE Signal Processing Letters, vol. 15, pp.565-568, 2008.
[30] Y. Li, Y. Du, and X. Lin, “Kernel-Based Multifactor Analysis for Image Synthesis and Recognition,” Proc. IEEE Int'l Conf. Computer Vision, pp.114-119, 2005.
[31] S.W. Park and M. Savvides, “Individual Kernel Tensor-Subspaces for Robust Face Recognition: A Computationally Efficient Tensor Framework Without Requiring Mode Factorization,” IEEE Trans. Systems, Man, and Cybernetics, Part B, vol. 37, no. 5, pp.1156-1166, Oct. 2007.
[32] Y. Du and X. Lin, “Emotional Facial Expression Model Building,” Pattern Recognition Letters, vol. 24, pp.2923-2934, 2003.
[33] H. Chen, P. Belhumeur, and D. Jacobs, “In Search of illumination Invariants,” Proc. IEEE Int'l Conf. Computer Vision and Pattern Recognition, pp.254-261, 2000.
[34] B. Jun and D. Kim, “Robust Real-Time Face Detection Using Face Certainty Map,” Proc. Int'l Conf. Biometrics, pp.29-38, 2007.
[35] D. Lin, Y. Xu, X. Tang, and S. Yan, “Tensor-Based Factor Decomposition for Relighting,” Proc. Int'l Conf. Image Processing, 2005.
[36] L. de Lathauwer, B. de Moor, and J. Vandewalle, “On the Best Rank-1 and Rank-($R_1, R_2, \ldots, R_N$ ) Approximation of Higher-Order Tensors,” SIAM J. Matrix Analysis and Applications, vol. 21, no. 4, pp.1324-1342, 2000.
[37] I. Matthews, S. Baker, and R. Gross, “Lucas-Kanade 20 Years on: A Unifying Framework: Part 3,” Robotics Inst., Nov. 2003.
[38] B. Lucas and T. Kanade, “An Iterative Image Registration Technique with an Application to Stereo Vision,” Proc. Int'l Joint Conf. Artificial Intelligence, pp.674-679, 1981.
[39] H.-S. Lee, S. Park, B. Kang, J. Shin, J.-Y. Lee, H.-M. Je, B. Jun, and D. Kim, “The POSTECH Face Database (PF07) and Performance Evaluation,” Proc. IEEE Int'l Conf. Automatic Face and Gesture Recognition, 2008.
6 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool