Optimal Regions for Linear Model-Based 3D Face Reconstruction

  • Michaël De Smet
  • Luc Van Gool
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6494)


In this paper, we explore region-based 3D representations of the human face. We begin by noting that although they serve as a key ingredient in many state-of-the-art 3D face reconstruction algorithms, very little research has gone into devising strategies for optimally designing them. In fact, the great majority of such models encountered in the literature is based on manual segmentations of the face into subregions. We propose algorithms that are capable of automatically finding the optimal subdivision given a training set and the number of desired regions. The generality of the segmentation approach is demonstrated on examples from the TOSCA database, and a cross-validation experiment on facial data shows that part-based models designed using the proposed algorithms are capable of outperforming alternative segmentations w.r.t. reconstruction accuracy.


Principal Component Analysis Face Recognition Reconstruction Error Object Class Manual Segmentation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Biederman, I.: Recognition-by-components: A theory of human image understanding. Psychological Review 94, 115–147 (1987)CrossRefGoogle Scholar
  2. 2.
    Brunelli, R., Poggio, T.: Face recognition: Features versus templates. IEEE T. Pattern Anal. 15, 1042–1052 (1993)CrossRefGoogle Scholar
  3. 3.
    Pentland, A., Moghaddam, B., Starner, T.: View-based and modular eigenspaces for face recognition. In: Proc. CVPR, pp. 84–91 (1994)Google Scholar
  4. 4.
    Martínez, A.M.: Recognizing imprecisely localized, partially occluded, and expression variant faces from a single sample per class. IEEE T. Pattern Anal. 24, 748–763 (2002)CrossRefGoogle Scholar
  5. 5.
    Tarrés, F., Rama, A., Torres, L.: A novel method for face recognition under partial occlusion or facial expression variations. In: Proc. ELMAR, pp. 163–166 (2005)Google Scholar
  6. 6.
    Faltemier, T.C., Bowyer, K.W., Flynn, P.J.: A region ensemble for 3-D face recognition. IEEE T. Inf. Foren. Sec. 3, 62–73 (2008)CrossRefGoogle Scholar
  7. 7.
    Blanz, V., Vetter, T.: A morphable model for the synthesis of 3D faces. In: Proc. SIGGRAPH, pp. 187–194 (1999)Google Scholar
  8. 8.
    Peyras, J., Bartoli, A., Mercier, H., Dalle, P.: Segmented AAMs improve person-independent face fitting. In: Proc. BMVC (2007)Google Scholar
  9. 9.
    Blanz, V., Vetter, T.: Face recognition based on fitting a 3D morphable model. IEEE T. Pattern Anal. 25, 1063–1074 (2003)CrossRefGoogle Scholar
  10. 10.
    Mian, A., Bennamoun, M., Owens, R.: Region-based matching for robust 3D face recognition. In: Proc. BMVC, vol. 1, pp. 199–208 (2005)Google Scholar
  11. 11.
    Basso, C., Verri, A.: Fitting 3D morphable models using implicit representations. In: Proc. GRAPP, pp. 45–52 (2007)Google Scholar
  12. 12.
    Kakadiaris, I.A., Passalis, G., Toderici, G., Murtuza, M.N., Lu, Y., Karampatziakis, N., Theoharis, T.: Three-dimensional face recognition in the presence of facial expressions: An annotated deformable model approach. IEEE T. Pattern Anal. 29, 640–649 (2007)CrossRefGoogle Scholar
  13. 13.
    Zhang, Y., Xu, S.: Data-driven feature-based 3D face synthesis. In: Proc. 3DIM, pp. 39–46 (2007)Google Scholar
  14. 14.
    ter Haar, F.B., Veltkamp, R.C.: 3D face model fitting for recognition. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part IV. LNCS, vol. 5305, pp. 652–664. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  15. 15.
    Shamir, A.: A survey on mesh segmentation techniques. Comput. Graph. Forum 27, 1539–1556 (2008)CrossRefzbMATHGoogle Scholar
  16. 16.
    Joshi, P., Tien, W.C., Desbrun, M., Pighin, F.H.: Learning controls for blend shape based realistic facial animation. In: Proc. SIGGRAPH (2003)Google Scholar
  17. 17.
    Lee, D.D., Seung, H.S.: Learning the parts of objects by non-negative matrix factorization. Nature 401, 788–791 (1999)CrossRefGoogle Scholar
  18. 18.
    Hoyer, P.O.: Non-negative matrix factorization with sparseness constraints. J. Mach. Learn. Res. 5, 1457–1469 (2004)MathSciNetzbMATHGoogle Scholar
  19. 19.
    Zass, R., Shashua, A.: Nonnegative sparse PCA. In: NIPS, pp. 1561–1568 (2006)Google Scholar
  20. 20.
    Stauffer, C., Grimson, W.L.: Similarity templates for detection and recognition. In: Proc. CVPR, pp. 221–230 (2001)Google Scholar
  21. 21.
    Basso, C., Paysan, P., Vetter, T.: Registration of expressions data using a 3D morphable model. In: Proc. FG, pp. 205–210 (2006)Google Scholar
  22. 22.
    Kirby, M., Sirovich, L.: Application of the karhunen-loeve procedure for the characterization of human faces. IEEE T. Pattern Anal. 12, 103–108 (1990)CrossRefGoogle Scholar
  23. 23.
    Penev, P.S., Sirovich, L.: The global dimensionality of face space. In: Proc. FG, pp. 264–270 (2000)Google Scholar
  24. 24.
    Yang, Q., Ding, X.: Symmetrical PCA in face recognition. In: Proc. ICIP, vol. 2, pp. 97–100 (2002)Google Scholar
  25. 25.
    Arthur, D., Vassilvitskii, S.: k-means++: The advantages of careful seeding. In: Proc. SODA, pp. 1027–1035 (2007)Google Scholar
  26. 26.
    Bronstein, A., Bronstein, M., Kimmel, R.: Numerical Geometry of Non-Rigid Shapes. Springer Publishing Company, Incorporated, Heidelberg (2008)zbMATHGoogle Scholar
  27. 27.
    Berry, M.W., Browne, M., Langville, A.N., Pauca, V.P., Plemmons, R.J.: Algorithms and applications for approximate nonnegative matrix factorization. Comput. Stat. Data An. 52, 155–173 (2007)MathSciNetCrossRefzbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Michaël De Smet
    • 1
  • Luc Van Gool
    • 1
  1. 1.K.U. Leuven ESAT-PSI/VISICSHeverleeBelgium

Personalised recommendations