publication . Other literature type . Article . Preprint . 2018

Deep Appearance Models: A Deep Boltzmann Machine Approach for Face Modeling

Chi Nhan Duong; Kha Gia Quach;
Open Access
  • Published: 31 Aug 2018
  • Publisher: Springer Science and Business Media LLC
Abstract
The "interpretation through synthesis" approach to analyze face images, particularly Active Appearance Models (AAMs) method, has become one of the most successful face modeling approaches over the last two decades. AAM models have ability to represent face images through synthesis using a controllable parameterized Principal Component Analysis (PCA) model. However, the accuracy and robustness of the synthesized faces of AAM are highly depended on the training sets and inherently on the generalizability of PCA subspaces. This paper presents a novel Deep Appearance Models (DAMs) approach, an efficient replacement for AAMs, to accurately capture both shape and text...
Subjects
ACM Computing Classification System: ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
free text keywords: Software, Artificial Intelligence, Computer Vision and Pattern Recognition, Computer Science - Computer Vision and Pattern Recognition
Related Organizations
Funded by
NSERC
Project
  • Funder: Natural Sciences and Engineering Research Council of Canada (NSERC)
64 references, page 1 of 5

[1] T. F. Cootes, G. J. Edwards, and C. J. Taylor, “Interprettting Face Images using Active Appearance Models,” in FG, 1998, pp. 300-305. [OpenAIRE]

[2] G. J. Edwards, T. F. Cootes, and C. J. Taylor, “Face recognition using active appearance models,” in ECCV. Springer, 1998, pp. 581-595. [OpenAIRE]

[3] J. Sung and D. Kim, “Pose-robust facial expression recognition using view-based 2D + 3D AAM,” TSMC, vol. 38, no. 4, pp. 852-866, 2008.

[4] J. Zhu, S. C. Hoi, and M. R. Lyu, “Real-time non-rigid shape recovery via active appearance models for augmented reality,” in ECCV. Springer, 2006, pp. 186-197.

[5] R. Anderson, B. Stenger, V. Wan, and R. Cipolla, “Expressive visual text-to-speech using active appearance models,” in CVPR. IEEE, 2013, pp. 3382-3389. [OpenAIRE]

[6] R. Gross, I. Matthews, and S. Baker, “Generic vs. person specific active appearance models,” Image and Vision Computing, vol. 23, no. 12, pp. 1080-1093, 2005.

[7] T. F. Cootes and C. J. Taylor, “An algorithm for tuning an active appearance model to new data.” in BMVC, 2006, pp. 919-928. [OpenAIRE]

[8] D. Pizarro, J. Peyras, and A. Bartoli, “Light-invariant fitting of active appearance models,” in CVPR. IEEE, 2008, pp. 1-6.

[9] I. Matthews and S. Baker, “Active appearance models revisited,” IJCV, vol. 60, no. 2, pp. 135-164, 2004.

[10] R. Donner, M. Reiter, G. Langs, P. Peloschek, and H. Bischof, “Fast active appearance model search using canonical correlation analysis,” TPAMI, vol. 28, no. 10, p. 1690, 2006.

[11] B. Amberg, A. Blake, and T. Vetter, “On compositional image alignment, with an application to active appearance models,” in CVPR. IEEE, 2009, pp. 1714-1721. [OpenAIRE]

[12] S. Z. Joan Alabort-i Medina, “Bayesian active appearance models,” in CVPR. IEEE, 2014, pp. 3438-3445. [OpenAIRE]

[13] R. Salakhutdinov and G. E. Hinton, “Deep boltzmann machines,” in Intl. Conf. on Artificial Intell. and Statistics, 2009, pp. 448-455.

[14] S. A. Eslami, N. Heess, C. K. Williams, and J. Winn, “The shape boltzmann machine: a strong model of object shape,” IJCV, vol. 107, no. 2, pp. 155-176, 2014.

[15] Y. Wu, Z. Wang, and Q. Ji, “Facial feature tracking under varying facial expressions and face poses based on restricted boltzmann machines,” in CVPR. IEEE, 2013, pp. 3452-3459.

64 references, page 1 of 5
Abstract
The "interpretation through synthesis" approach to analyze face images, particularly Active Appearance Models (AAMs) method, has become one of the most successful face modeling approaches over the last two decades. AAM models have ability to represent face images through synthesis using a controllable parameterized Principal Component Analysis (PCA) model. However, the accuracy and robustness of the synthesized faces of AAM are highly depended on the training sets and inherently on the generalizability of PCA subspaces. This paper presents a novel Deep Appearance Models (DAMs) approach, an efficient replacement for AAMs, to accurately capture both shape and text...
Subjects
ACM Computing Classification System: ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
free text keywords: Software, Artificial Intelligence, Computer Vision and Pattern Recognition, Computer Science - Computer Vision and Pattern Recognition
Related Organizations
Funded by
NSERC
Project
  • Funder: Natural Sciences and Engineering Research Council of Canada (NSERC)
64 references, page 1 of 5

[1] T. F. Cootes, G. J. Edwards, and C. J. Taylor, “Interprettting Face Images using Active Appearance Models,” in FG, 1998, pp. 300-305. [OpenAIRE]

[2] G. J. Edwards, T. F. Cootes, and C. J. Taylor, “Face recognition using active appearance models,” in ECCV. Springer, 1998, pp. 581-595. [OpenAIRE]

[3] J. Sung and D. Kim, “Pose-robust facial expression recognition using view-based 2D + 3D AAM,” TSMC, vol. 38, no. 4, pp. 852-866, 2008.

[4] J. Zhu, S. C. Hoi, and M. R. Lyu, “Real-time non-rigid shape recovery via active appearance models for augmented reality,” in ECCV. Springer, 2006, pp. 186-197.

[5] R. Anderson, B. Stenger, V. Wan, and R. Cipolla, “Expressive visual text-to-speech using active appearance models,” in CVPR. IEEE, 2013, pp. 3382-3389. [OpenAIRE]

[6] R. Gross, I. Matthews, and S. Baker, “Generic vs. person specific active appearance models,” Image and Vision Computing, vol. 23, no. 12, pp. 1080-1093, 2005.

[7] T. F. Cootes and C. J. Taylor, “An algorithm for tuning an active appearance model to new data.” in BMVC, 2006, pp. 919-928. [OpenAIRE]

[8] D. Pizarro, J. Peyras, and A. Bartoli, “Light-invariant fitting of active appearance models,” in CVPR. IEEE, 2008, pp. 1-6.

[9] I. Matthews and S. Baker, “Active appearance models revisited,” IJCV, vol. 60, no. 2, pp. 135-164, 2004.

[10] R. Donner, M. Reiter, G. Langs, P. Peloschek, and H. Bischof, “Fast active appearance model search using canonical correlation analysis,” TPAMI, vol. 28, no. 10, p. 1690, 2006.

[11] B. Amberg, A. Blake, and T. Vetter, “On compositional image alignment, with an application to active appearance models,” in CVPR. IEEE, 2009, pp. 1714-1721. [OpenAIRE]

[12] S. Z. Joan Alabort-i Medina, “Bayesian active appearance models,” in CVPR. IEEE, 2014, pp. 3438-3445. [OpenAIRE]

[13] R. Salakhutdinov and G. E. Hinton, “Deep boltzmann machines,” in Intl. Conf. on Artificial Intell. and Statistics, 2009, pp. 448-455.

[14] S. A. Eslami, N. Heess, C. K. Williams, and J. Winn, “The shape boltzmann machine: a strong model of object shape,” IJCV, vol. 107, no. 2, pp. 155-176, 2014.

[15] Y. Wu, Z. Wang, and Q. Ji, “Facial feature tracking under varying facial expressions and face poses based on restricted boltzmann machines,” in CVPR. IEEE, 2013, pp. 3452-3459.

64 references, page 1 of 5
Powered by OpenAIRE Research Graph
Any information missing or wrong?Report an Issue