Abstract
Facial point detection is an active area in computer vision due to its relevance to many applications. It is a nontrivial task, since facial shapes vary significantly with facial expressions, poses or occlusion. In this paper, we address this problem by proposing a discriminative deep face shape model that is constructed based on an augmented factorized three-way Restricted Boltzmann Machines model. Specifically, the discriminative deep model combines the top-down information from the embedded face shape patterns and the bottom up measurements from local point detectors in a unified framework. In addition, along with the model, effective algorithms are proposed to perform model learning and to infer the true facial point locations from their measurements. Based on the discriminative deep face shape model, 68 facial points are detected on facial images in both controlled and “in-the-wild” conditions. Experiments on benchmark data sets show the effectiveness of the proposed facial point detection algorithm against state-of-the-art methods.
Similar content being viewed by others
References
Baker, S., Gross, R., & Matthews, I. (2002). Lucas-kanade 20 years on: A unifying framework: Part 3. International Journal of Computer Vision, 56, 221–255.
Belhumeur, P., Jacobs, D., Kriegman, D., & Kumar, N. (2013). Localizing parts of faces using a consensus of exemplars. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(12), 2930–2940.
Belhumeur, P. N., Jacobs, D. W., Kriegman, D. J., & Kumar, N. (2011). Localizing parts of faces using a consensus of exemplars. In IEEE International Conference on Computer Vision and Pattern Recognition.
Cootes, T. F., Taylor, C. J., Cooper, D. H., & Graham, J. (1995). Active shape models their training and application. Computer Vision and Image Understanding, 61(1), 38–59.
Cootes, T. F., Edwards, G. J., & Taylor, C. J. (2001). Active appearance models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(6), 681–685.
Cristinacce, D., & Cootes, T. (2008). Automatic feature localisation with constrained local models. Pattern Recognition, 41(10), 3054–3067.
Dalal, N., & Triggs, B. (2005). Histograms of oriented gradients for human detection. International Conference on Computer Vision and Pattern Recognition, 2, 886–893.
Eslami, S., Heess, N., & Winn, J. (2012). The shape boltzmann machine: A strong model of object shape. In IEEE Conference on Computer Vision and Pattern Recognition (pp. 406–413).
Fan, R. E., Chang, K. W., Hsieh, C. J., Wang, X. R., & Lin, C. J. (2008). LIBLINEAR: A library for large linear classification. Journal of Machine Learning Research, 9, 1871–1874.
Gross, R., Matthews, I., Cohn, J., Kanade, T., & Baker, S. (2010). Multi-pie. Image and Vision Computing, 28(5), 807–813.
Hinton, G. E. (2002). Training products of experts by minimizing contrastive divergence. Neural Computation, 14(8), 1771–1800.
Hinton, G. E., & Salakhutdinov, R. R. (2006). Reducing the dimensionality of data with neural networks. Science, 313(5786), 504–507.
Kae, A., Sohn, K., Lee, H., & Learned-Miller, E. G. (2013). Augmenting crfs with boltzmann machine shape priors for image labeling. In IEEE Conference on Computer Vision and Pattern Recognition (pp. 2019–2026).
Le, V., Brandt, J., Lin, Z., Bourdev, L., & Huang, T. S. (2012). Interactive facial feature localization. In European Conference on Computer Vision, Part III (ECCV’12, pp. 679–692).
Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International Journal on Computer Vision, 60(2), 91–110.
Martinez, B., Valstar, M. F., Binefa, X., & Pantic, M. (2013). Local evidence aggregation for regression-based facial point detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(5), 1149–1163.
Matthews, I., & Baker, S. (2004). Active appearance models revisited. International Journal of Computer Vision, 60(2), 135–164.
Memisevic, R., & Hinton, G. E. (2010). Learning to represent spatial transformations with factored higher-order boltzmann machines. Neural Computation, 22(6), 1473–1492.
Mohamed, A., Dahl, G., & Hinton, G. (2011). Acoustic modeling using deep belief networks. IEEE Transactions on Audio, Speech, and Language Processing, PP(99), 1.
Ranzato, M., Krizhevsky, A., & Hinton, G. E. (2010). Factored 3-way restricted boltzmann machines for modeling natural images. In International Conference on Artificial Intelligence and Statistics (pp. 621–628).
Sagonas, C., Tzimiropoulos, G., Zafeiriou, S., Pantic, M. (2013). 300 faces in-the-wild challenge: The first facial landmark localization challenge. In Proceedings of IEEE International Conference on Computer Vision (ICCV-W 2013), Sydney.
Sagonas, C., Tzimiropoulos, G., Zafeiriou, S., & Pantic, M. (2013). A semi-automatic methodology for facial landmark annotation. In Computer Vision and Pattern Recognition Workshops (CVPRW, pp. 896–903).
Salakhutdinov, R., & Hinton, G. (2009). Deep boltzmann machines. Proceedings of the International Conference on Artificial Intelligence and Statistics, 5, 448–455.
Saragih, J. M., Lucey, S., & Cohn, J. F. (2011). Deformable model fitting by regularized landmark mean-shift. International Journal of Computer Vision, 91(2), 200–215.
Smola, A. J., & Schölkopf, B. (2004). A tutorial on support vector regression. Statistics and Computing, 14(3), 199–222.
Sun, Y., Wang, X., & Tang, X. (2013a). Deep convolutional network cascade for facial point detection. In IEEE International Conference on Computer Vision and Pattern Recognition (pp. 3476–3483).
Sun, Y., Wang, X., & Tang, X. (2013b). Hybrid deep learning for face verification. In 2013 IEEE International Conference on Computer Vision (ICCV), pp. 1489–1496.
Taigman, Y., Yang, M., Ranzato, M., & Wolf, L. (2014). DeepFace: Closing the gap to human-level performance in face verification. In 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1701–1708.
Taylor, G., Sigal, L., Fleet, D., & Hinton, G. (2010). Dynamical binary latent variable models for 3d human pose tracking. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR, pp. 631–638).
Tieleman, T. (2008). Training restricted boltzmann machines using approximations to the likelihood gradient. In Proceedings of the 25th International Conference on Machine Learning (pp. 1064–1071).
Tzimiropoulos, G., & Pantic, M. (2013). Optimization problems for fast aam fitting in-the-wild. In International conference on Computer Vision (pp. 593–600).
Valstar, M., Martinez, B., Binefa, V., & Pantic, M. (2010). Facial point detection using boosted regression and graph models. In IEEE International Conference on Computer Vision and Pattern Recognition (pp. 13–18).
Welling, M., & Hinton, G. E. (2002). A new learning algorithm for mean field boltzmann machines. In Proceedings of the International Conference on Artificial Neural Networks (ICANN ’02, pp 351–357). London: Springer.
Wu, Y., Wang, Z., & Ji, Q. (2013). Facial feature tracking under varying facial expressions and face poses based on restricted boltzmann machines. In IEEE Conference on Computer Vision and Pattern Recognition (pp. 3452–3459).
Xiong, X., & De la Torre Frade, F. (2013). Supervised descent method and its applications to face alignment. In IEEE International Conference on Computer Vision and Pattern Recognition (CVPR).
Zhou, E., Fan, H., Cao, Z., Jiang, Y., & Yin, Q. (2013). Extensive facial landmark localization with coarse-to-fine convolutional network cascade. In IEEE International Conference on Computer Vision Workshops (pp. 386–391).
Zhu, X., & Ramanan, D. (2012). Face detection, pose estimation, and landmark localization in the wild. In IEEE International Conference on Computer Vision and Pattern Recognition (pp. 2879–2886).
Acknowledgments
This work is supported in part by a Grant from US Army Research office (W911NF-12-C-0017).
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by Marc’Aurelio Ranzato, Geoffrey E. Hinton, and Yann Lecun.
Rights and permissions
About this article
Cite this article
Wu, Y., Ji, Q. Discriminative Deep Face Shape Model for Facial Point Detection. Int J Comput Vis 113, 37–53 (2015). https://doi.org/10.1007/s11263-014-0775-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11263-014-0775-8