Facial Parts-Based Face Hallucination Method

  • Kaori Kataoka
  • Shingo Ando
  • Akira Suzuki
  • Hideki Koike
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6134)

Abstract

Face hallucination produces high-resolution facial images from low-resolution inputs. In this paper, we propose a facial-parts-based face hallucination method. Since our goal is face recognition rather than face reconstruction, the contour information of facial-parts(such as eyes) is important. This method reconstructs facial parts as entities instead of dividing them into small blocks. We obtain the contours of facial parts by using the Active Appearance Model(AAM), and transform training images based on contours. We confirm that the proposed method significantly enhances face recognition performance.

Keywords

face hallucination contour of facial-parts Active Appearance Model 

References

  1. 1.
    Baker, S., Kanade, T.: Hallucinating faces. In: Proceedings of the IEEE International Conference on Automatic Face and Gesture Recognition, Grenoble, France, pp. 83–88 (2000)Google Scholar
  2. 2.
    Wang, X.G., Tang, X.O.: Hallucinating face by eigentransformation. IEEE Trans. Syst. Man. Cybern. 35(3), 425–434 (2005)CrossRefGoogle Scholar
  3. 3.
    Chang, H., Yeung, D.Y., Xiong, Y.M.: Super-resolution through neighbor embedding. In: Proceedings of CVPR’04, Washington, DC, vol. 1, pp. 275–282 (2004)Google Scholar
  4. 4.
    Liu, C., Shum, H., Freeman, W.T.: Face hallucination: Theory and practice. Int. J. Comput. Vis. 75(1), 115–134 (2007)Google Scholar
  5. 5.
    Li, Y., Lin, X.: An improved two-step approach to hallucinating faces. In: Proc. IEEE Conf. Image and Graphics, December 2004, pp. 298–301 (2004)Google Scholar
  6. 6.
    Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active appearance models. In: Proc. of the 5th European Conference on Computer Vision, vol. 2, pp. 484–498. Springer, Heidelberg (1998)Google Scholar
  7. 7.
    Moriyama, T., Kanade, T., Xiao, J., Cohn, J.F.: Meticulously detailed eye region model and its application to analysis of facial images. IEEE Transactions on Pattern Analysis and Machine Intelligence 28(5), 738–752 (2006)Google Scholar
  8. 8.

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Kaori Kataoka
    • 1
  • Shingo Ando
    • 2
  • Akira Suzuki
    • 1
  • Hideki Koike
    • 1
  1. 1.NTT Cyber Space LaboratoriesNTT CorporationKanagawaJapan
  2. 2.Research and Development CenterNippon Telegraph and Telephone West CorporationOsakaJapan

Personalised recommendations