Advertisement

Reconstructing 3D Face Shapes from Single 2D Images Using an Adaptive Deformation Model

  • Ashraf Y. A. Maghari
  • Ibrahim Venkat
  • Iman Yi Liao
  • Bahari Belaton
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8237)

Abstract

The Representational Power (RP) of an example-based model is its capability to depict a new 3D face for a given 2D face image. In this contribution, a novel approach is proposed to increase the RP of the 3D reconstruction PCA-based model by deforming a set of examples in the training dataset. By adding these deformed samples together with the original training samples we gain more RP. A 3D PCA-based model is adapted for each new input face image by deforming 3D faces in the training data set. This adapted model is used to reconstruct the 3D face shape for the given input 2D near frontal face image. Our experimental results justify that the proposed adaptive model considerably improves the RP of the conventional PCA-based model.

Keywords

Representational Power Statistical facial modeling 3D face reconstruction PCA TPS 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Atick, J., Griffin, P., Redlich, A.: Statistical approach to shape from shading: Reconstruction of three-dimensional face surfaces from single two-dimensional images. Neural Computation 8(6), 1321–1340 (1996)CrossRefGoogle Scholar
  2. 2.
    Besl, P., McKay, H.: A method for registration of 3D shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence 14(2), 239–256 (1992)CrossRefGoogle Scholar
  3. 3.
    Blanz, V., Vetter, T.: Face recognition based on fitting a 3D morphable model. IEEE Transactions on Pattern Analysis and Machine Intelligence 25(9), 1063–1074 (2003)CrossRefGoogle Scholar
  4. 4.
    Blanz, V., Vetter, T.: A morphable model for the synthesis of 3D faces. In: Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1999, pp. 187–194. ACM Press/Addison-Wesley Publishing Co., New York (1999), http://dx.doi.org/10.1145/311535.311556 CrossRefGoogle Scholar
  5. 5.
    Bookstein, F.L.: Principal warps: Thin-plate splines and the decomposition of deformations. IEEE Transactions on Pattern Analysis and Machine Intelligence 11(6), 567–585 (1989)CrossRefzbMATHGoogle Scholar
  6. 6.
    Bottino, A., De Simone, M., Laurentini, A., Sforza, C.: A new 3D tool for planning plastic surgery. IEEE Transactions on Bio-medical Engineering (2012)Google Scholar
  7. 7.
    Brown, B., Rusinkiewicz, S.: Non-rigid range-scan alignment using thin-plate splines. In: Proceedings of the 2nd International Symposium on 3D Data Processing, Visualization and Transmission, 3DPVT 2004, pp. 759–765. IEEE (2004)Google Scholar
  8. 8.
    Elyan, E., Ugail, H.: Reconstruction of 3D human facial images using partial differential equations. JCP, 1–8 (2007)Google Scholar
  9. 9.
    Fanany, M.I., Ohno, M., Kumazawa, I.: Face Reconstruction from Shading Using Smooth Projected Polygon Representation NN. In: Proceedings of the 15th International Conference on Vision Interface, Calgary, Canada, pp. 308–313 (May 2002)Google Scholar
  10. 10.
    Farkas, L.G.: Anthropometry of the head and face, 2nd edn. Raven Press (1994)Google Scholar
  11. 11.
    Hu, Y., Jiang, D., Yan, S., Zhang, L.: Automatic 3D reconstruction for face recognition. In: Proceedings of the Sixth IEEE International Conference on Automatic Face and Gesture Recognition, pp. 843–848. IEEE (2004)Google Scholar
  12. 12.
    Jiang, D., Hu, Y., Yan, S., Zhang, L., Zhang, H., Gao, W.: Efficient 3D reconstruction for face recognition. Pattern Recogn. 38, 787–798 (2005), http://dx.doi.org/10.1016/j.patcog.2004.11.004 CrossRefGoogle Scholar
  13. 13.
    Kemelmacher-Shlizerman, I., Basri, R.: 3D face reconstruction from a single image using a single reference face shape. IEEE Transactions on Pattern Analysis and Machine Intelligence 33(2), 394–405 (2011)CrossRefGoogle Scholar
  14. 14.
    Knothe, R., Romdhani, S., Vetter, T.: Combining PCA and LFA for surface reconstruction from a sparse set of control points. In: 7th International Conference on Automatic Face and Gesture Recognition, FGR 2006, pp. 637–644. IEEE (2006)Google Scholar
  15. 15.
    Levine, M.D. (Chris) Yu, Y.: State-of-the-art of 3D facial reconstruction methods for face recognition based on a single 2D training image per person. Pattern Recogn. Lett. 30, 908–913 (2009), http://dl.acm.org/citation.cfm?id=1552570.1552692 CrossRefGoogle Scholar
  16. 16.
    Lin, C., Cheng, W., Liang, S.: Neural-network-based adaptive hybrid-reflectance model for 3D surface reconstruction. IEEE Transactions on Neural Networks 16(6), 1601–1615 (2005)CrossRefGoogle Scholar
  17. 17.
    Lu, X., Jain, A.: Deformation modeling for robust 3D face matching. IEEE Transactions on Pattern Analysis and Machine Intelligence 30(8), 1346–1357 (2008)CrossRefGoogle Scholar
  18. 18.
    Luximon, Y., Ball, R., Justice, L.: The 3D chinese head and face modeling. Computer-Aided Design 44(1), 40–47 (2012), digital Human Modeling in Product Design, http://www.sciencedirect.com/science/article/pii/S0010448511000133
  19. 19.
    Maghari, A.Y.A., Liao, I.Y., Belaton, B.: Effect of facial feature points selection on 3D face shape reconstruction using regularization. In: Huang, T., Zeng, Z., Li, C., Leung, C.S. (eds.) ICONIP 2012, Part V. LNCS, vol. 7667, pp. 516–524. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  20. 20.
    Maghari, A., Liao, I., Belaton, B.: Quantitative analysis on PCA-based statistical 3D face shape modeling. In: Computational Modelling of Objects Represented in Images III: Fundamentals, Methods and Applications, vol. 13 (2012)Google Scholar
  21. 21.
    Romdhani, S., Blanz, V., Vetter, T.: Face identification by fitting a 3D morphable model using linear shape and texture error functions. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002, Part IV. LNCS, vol. 2353, pp. 3–19. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  22. 22.
    Sim, T., Baker, S., Bsat, M.: The CMU pose, illumination, and expression database. IEEE Transactions on Pattern Analysis and Machine Intelligence 25(12), 1615–1618 (2003)CrossRefGoogle Scholar
  23. 23.
    Smith, W., Hancock, E.: Recovering facial shape using a statistical model of surface normal direction. IEEE Transactions on Pattern Analysis and Machine Intelligence 28(12), 1914–1930 (2006)CrossRefGoogle Scholar
  24. 24.
    Wahba, G.: Spline models for observational data, vol. 59. Society for Industrial Mathematics (1990)Google Scholar
  25. 25.
    Wang, S.F., Lai, S.H.: Reconstructing 3D face model with associated expression deformation from a single face image via constructing a low-dimensional expression deformation manifold. IEEE Transactions on Pattern Analysis and Machine Intelligence 33(10), 2115–2121 (2011)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2013

Authors and Affiliations

  • Ashraf Y. A. Maghari
    • 1
  • Ibrahim Venkat
    • 1
  • Iman Yi Liao
    • 2
  • Bahari Belaton
    • 1
  1. 1.School of Computer SciencesUniversiti Sains MalaysiaPinangMalaysia
  2. 2.School of Computer ScienceUniversity of Nottingham Malaysia CampusMalaysia

Personalised recommendations