Recovering Facial Intrinsic Images from a Single Input

  • Ming Shao
  • Yun-Hong Wang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5754)


According to Barrow and Tenenbaum’s theory, an image can be decomposed into two images: a reflectance image and an illumination image. This midlevel description of images attracts more and more attentions recently owing to its application in computer vision, i.e. facial image processing and face recognition. However, due to its ill-posed characteristics, this decomposition remains difficult. In this paper, we concentrate on a slightly easier problem: given a simple frontal facial image and a learned near infrared image, could we recover its reflectance image? Experiments show that it is feasible and promising. Based on extensive study on hyperspectral images, skin color model and Quotient Image, we proposed a method to derive reflectance images through division operations. That is to divide visual frontal face images by learned near infrared images which are generated by super-resolution in tensor space. With the operation on grey distribution of frontal facial images, the results after division can represent the reflectance of skin, rarely bearing any illumination information. Experimental results show that our method is reasonable and promising in image synthesis, processing and face recognition.


Intrinsic images near infrared super-resolution Tensorfaces Multi-Spectral Quotient Image 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Georghiades, A.S., Belhumeur, P.N., Kriegman, D.J.: From Few to Many: Illumination Cone Models for Face Recognition Under Variable Lighting and Pose. IEEE Trans. Pattern Anal. Mach. Intell. 23(6), 643–660 (2001)CrossRefGoogle Scholar
  2. 2.
    Shashua, A., Riklin-Raviv, T.: The Quotient Image: Class-based Re-rendering and Recognition with Varying Illuminations. IEEE Trans. Pattern Anal. Mach. Intell. 23(2), 129–139 (2001)CrossRefGoogle Scholar
  3. 3.
    Basri, R., Jacobs, D.: Lambertian Reflectance and Linear Subspaces. IEEE Trans. Pattern Anal. Mach. Intell. 25(2), 218–233 (2003)CrossRefGoogle Scholar
  4. 4.
    Ramamoorthi, R., Hanrahan, P.: On the Relationship Between Radiance and Irradiance: Determining the Illumination from Images of a Convex Lambertian Object. JOSA A 18(10), 2448–2459 (2001)CrossRefMathSciNetGoogle Scholar
  5. 5.
    Blanz, V., Vetter, T.: Morphable Model for the Synthesis of 3D Faces. In: Proc. ACM SIGGRAPH (1999)Google Scholar
  6. 6.
    Vasilescu, M.A.O., Terzopoulos, D.: Multilinear Analysis of Image Ensembles: TensorFaces. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 447–460. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  7. 7.
    Barrow, H.G., Tenenbaum, J.M.: Recovering Intrinsic Scene Characteristics from Images. Computer Vision System (1978)Google Scholar
  8. 8.
    Weiss, Y.: Deriving Intrinsic Images from Image Sequences. In: Proc. of IEEE ICCV (2001)Google Scholar
  9. 9.
    Shim, H., Luo, J., Chen, T.: A Subspace Model-Based Approach to Face Relighting Under Unknown Lighting and Poses. IEEE Trans. Image Process 17(8), 1331–1341 (2008)CrossRefMathSciNetGoogle Scholar
  10. 10.
    Tuchin, V.: Tissue Optics: Light Scattering Methods and Instruments for Medical Diagnosis. SPIE Press, Bellingham (2000)Google Scholar
  11. 11.
    Anderson, R., Parrish, J.: The Optics of Human Skin. J. Investigative Dermatology 77(1), 13–19 (1981)CrossRefGoogle Scholar
  12. 12.
    Gemert, M., Jacques, S., Sternborg, H., Star, W.: Skin Optics. IEEE Trans. Biomedical Eng. 36(12), 1146–1154 (1989)CrossRefGoogle Scholar
  13. 13.
    Angelopoulou, E., Molana, R., Daniilidis, K.: Multispectral Skin Color for Modeling. In: Proc. of IEEE International Conference on Computer Vision and Pattern Recognition (2001)Google Scholar
  14. 14.
    Pan, Z., Healey, G., Prasad, M., Tromberg, B.: Face Recognition in Hyperspectral Images. IEEE Trans. Pattern Anal. Mach. Intell. 25(12), 1552–1560 (2003)CrossRefGoogle Scholar
  15. 15.
    Jia, K., Gong, S.: Multi-modal tensor face for simultaneous super-resolution and recognition. In: Proc. IEEE Int. Conf. Computer Vision (2005)Google Scholar
  16. 16.
    Wang, H., Li, S.Z., Wang, Y.: Face Recognition Under Varying Lighting Conditions Using Self Quotient Image. In: International Conference on FGR, pp. 819–824 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Ming Shao
    • 1
  • Yun-Hong Wang
    • 1
  1. 1.School of Computer Science and EngineeringBeihang UniversityBeijingChina

Personalised recommendations