Abstract
Facial landmark detection in the wild is challenging due to the appearance and shape variations caused by facial expressions, head poses, illuminations, and occlusions. To tackle this problem, we propose two probabilistic face shape models that could capture the face shape variations in different conditions. The first model is a undirected graphical model constructed based on the Restricted Boltzmann Machine (RBM). It decouples the shape variations into expression related and pose related parts. The second model is a directed hierarchical probabilistic model that specifically uses the head pose and expression labels in model construction. It embeds the local shape variations for each facial component, and automatically exploits the relationships among facial components, expressions and head poses. Experiments on benchmark databases show the effectiveness of the proposed probabilistic face shape models for facial landmark detection in the wild.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Murphy-Chutorian, E., Trivedi, M.: Head pose estimation in computer vision: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 31(4), 607–626 (2009)
Fasel, B., Luettin, J.: Automatic facial expression analysis: A survey. Pattern Recognition 36(1), 259–275 (1999)
Wu, Y., Wang, Z., Ji, Q.: 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 (2013)
Wu, Y., Wang, Z., Ji, Q.: A hierarchical probabilistic model for facial feature detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1781–1788 (2014)
Lucey, P., Cohn, J., Kanade, T., Saragih, J., Ambadar, Z., Matthews, I.: The extended cohn-kanade dataset (ck+): a complete dataset for action unit and emotion-specified expression. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 94–101 (2010)
Phillips, P., Moon, H., Rauss, P., Rizvi, S.: The feret evaluation methodology for face-recognition algorithms. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 137–143 (1997)
Tong, Y., Liao, W., Ji, Q.: Isl multi-view facial expression database. http://www.ecse.rpi.edu/ cvrl/database/database.html
Koestinger, M., Wohlhart, P., Roth, P.M., Bischof, H.: Annotated facial landmarks in the wild: a large-scale, real-world database for facial landmark localization. In: First IEEE International Workshop on Benchmarking Facial Image Analysis Technologies (2011)
Cootes, T.F., Taylor, C.J., Cooper, D.H., Graham, J.: Active shape models their training and application. Comput. Vis. Image Underst. 61(1), 38–59 (1995)
Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active appearance models. IEEE Transactions on Pattern Analysis and Machine Intelligence 23(6), 681–685 (2001)
Cristinacce, D., Cootes, T.: Automatic feature localisation with constrained local models. Pattern Recognition 41(10), 3054–3067 (2008)
Valstar, M., Martinez, B., Binefa, V., Pantic, M.: Facial point detection using boosted regression and graph models. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp. 13–18 (2010)
Martinez, B., Valstar, M.F., Binefa, X., Pantic, M.: Local evidence aggregation for regression-based facial point detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 35(5), 1149–1163 (2013)
Zhu, X., Ramanan, D.: Face detection, pose estimation, and landmark localization in the wild. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp. 2879–2886 (2012)
Xiong, X., De la Torre Frade, F.: Supervised descent method and its applications to face alignment. In: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), May 2013
Hinton, G.E., Osindero, S.: A fast learning algorithm for deep belief nets. Neural Computation 18, 1527–1554 (2006)
Ranzato, M., Krizhevsky, A., Hinton, G.E.: Factored 3-way restricted boltzmann machines for modeling natural images. Journal of Machine Learning Research 9, 621–628 (2010)
Hinton, G.E.: Training products of experts by minimizing contrastive divergence. Neural Comput. 14(8), 1771–1800 (2002)
Fan, R.-E., Chang, K.-W., Hsieh, C.-J., Wang, X.-R., Lin, C.-J.: LIBLINEAR: A library for large linear classification. Journal of Machine Learning Research 9, 1871–1874 (2008)
Friedman, N.: Learning belief networks in the presence of missing values and hidden variables. In: International Conference on Machine Learning, pp. 125–133. Morgan Kaufmann (1997)
Koller, D., Friedman, N.: Probabilistic Graphical Models: Principles and Techniques. MIT Press (2009)
Pantic, M., Valstar, M., Rademaker, R., Maat, L.: Web-based database for facial expression analysis. In: IEEE International Conference on Multimedia and Expo, ICME 2005, pp. 317–321 (2005)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Wu, Y., Ji, Q. (2015). Learning the Face Shape Models for Facial Landmark Detection in the Wild. In: Ji, Q., B. Moeslund, T., Hua, G., Nasrollahi, K. (eds) Face and Facial Expression Recognition from Real World Videos. FFER 2014. Lecture Notes in Computer Science(), vol 8912. Springer, Cham. https://doi.org/10.1007/978-3-319-13737-7_4
Download citation
DOI: https://doi.org/10.1007/978-3-319-13737-7_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-13736-0
Online ISBN: 978-3-319-13737-7
eBook Packages: Computer ScienceComputer Science (R0)