Abstract
A novel method, called dynamic component deforming model, is proposed to reconstruct the face shape from a 2D image based on feature points. Assuming that human face belongs to a linear class, principal components learned from a 3D face database are used in order to constrain the results. Different from the fixed components used in the traditional methods, the significance of each component is investigated while the most correlative ones are selected as the basic space. This novel representation is able to fit a more exact 3D shape for an individual than the known methods as the useless data are excluded. Comparison results show that the proposed method achieves good results on both contrived data with known ground truth together with real photographs.
This paper is partially supported by Program for New Century Excellent Talents in University (NCET).
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
Lee, Y.C., Terzopoulos, D., Waters, K.: Realistic face modeling for animation. In: Siggraph Proceeding, Los Angeles, USA, pp. 55–62 (1995)
Zha, H.B., Wang, P.: Realistic face modeling by registration of 3D mesh models and multi-view color images. In: Proceeding of the 8th Int. Conf. Computer Aided Design and Computer Graphics, Macao, China, pp. 217–222 (2003)
Pighin, F., Hecker, J.: Synthesizing realistic facial expressions from photographs. In: Proceedings of the 25th Annual Conference on Computer Graphics, Orlando, USA, pp. 75–84 (1998)
Liu, Z.C., Zhang, Z.Y., Jacobs, C.: Rapid modeling of animated faces from video. The Journal of Visualization and Computer Animation 12, 227–240 (2001)
Dimitrijevic, M., Ilic, S., Fua, P.: Accurate face models from uncalibrated and ill-lit video sequence. In: Proceeding of IEEE Conference on Computer Vision and Pattern Recognition, pp. 188–202. IEEE Computer Society Press, Washington, DC (2004)
Blanz, V., Vetter, T.: A morphable model for the synthesis of 3D-faces. In: SIGGRAPH 1999 Conference Proceedings, Los Angeles, USA, pp. 187–194 (1999)
Romdhani, S.: Face image analysis using a multiple feature fitting strategy. Ph.D. thesis, University of Basel, Switzerland (2005)
Hu, Y.L., Yin, B.C., Gu, C.L., Cheng, S.Q.: 3D Face reconstruction based on the improved morphable model. Chinese Journal of Computers 10, 1671–1679 (2005)
Wang, C.Z., Yin, B.C., Sun, Y.F., Hu, Y.L.: An improved 3D face modeling method based on morphable model. Acta Automatica Sinica 3, 232–239 (2007)
Chai, X.J., Shan, S.G., Qing, L.Y.: Pose and illumination invariant face recognition based on 3D face reconstruction. Journal of Software 3, 525–534 (2006)
Jiang, D.L., Hu, Y.X., Yan, S.C.: Efficient 3D reconstruction for face recognition. Pattern Recognition (6), 787–798 (2005)
Blanz, V., Vetter, T.: Reconstructing the complete 3D shape of faces from partial information. it+ti Oldenburg Verlag 6, 295–302 (2002)
Knothe, R., Romdhani, S., Vetter, T.: Combining PCA and LFA for surface reconstruction from a sparse set of control points. In: Proceeding of IEEE Conference on Automatic Face and Gesture Recognition, Southampton, UK, pp. 637–644. IEEE Computer Society Press, Los Alamitos (2006)
The BJUT-3D large-scale chinese face database. Technical Report No ISKL-TR-05-FMFR-001. Multimedia and Intelligent Software Technology Beijing Municipal Key Laboratory, Beijing University of Technology, 8 (2005)
Gong, X., Wang, G.Y.: Automatic 3D face segmentation based on facial feature extraction. In: Proceeding of IEEE Conference on Industrial Technology, Mumbai, India, pp. 1154–1159. IEEE Computer Society Press, Los Alamitos (2006)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gong, X., Wang, G. (2007). A Dynamic Component Deforming Model for Face Shape Reconstruction. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2007. Lecture Notes in Computer Science, vol 4841. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-76858-6_48
Download citation
DOI: https://doi.org/10.1007/978-3-540-76858-6_48
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-76857-9
Online ISBN: 978-3-540-76858-6
eBook Packages: Computer ScienceComputer Science (R0)