Learning of Optimal Illumination for Material Classification

  • Markus Jehle
  • Christoph Sommer
  • Bernd Jähne
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6376)


We present a method to classify materials in illumination series data. An illumination series is acquired using a device which is capable to generate arbitrary lighting environments covering nearly the whole space of the upper hemisphere. The individual images of the illumination series span a high-dimensional feature space. Using a random forest classifier different materials, which vary in appearance (which itself depends on the patterns of incoming illumination), can be distinguished reliably. The associated Gini feature importance allows for determining the features which are most relevant for the classification result. By linking the features to illumination patterns a proposition about optimal lighting for defect detection can be made, which yields valuable information for the selection and placement of light sources.


Random Forest Photometric Stereo Illumination Pattern Directional Light Source Automate Visual Inspection 
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.
    Varma, M., Zisserman, A.: A statistical approach to texture classification from single images. Int. J. Comput. Vision 62(1-2), 61–81 (2005)CrossRefGoogle Scholar
  2. 2.
    Liu, C., Sharan, L., Adelson, E.H., Rosenholtz, R.: Exploring features in a bayesian framework for material recognition. In: Proc. CVPR (2010)Google Scholar
  3. 3.
    Abuelgasim, A., Gopal, S., Irons, J., Strahler, A.: Classification of ASAS multiangle and multispectral measurements using artificial neural networks. Remote Sensing of Environment 57(2), 79–87 (1996)CrossRefGoogle Scholar
  4. 4.
    Hertzmann, A., Seitz, S.M.: Example-based photometric stereo: Shape reconstruction with general, varying BRDFs. PAMI 27(8), 1254–1264 (2005)Google Scholar
  5. 5.
    Koppal, S.J., Narasimhan, S.G.: Clustering appearance for scene analysis. In: Proc. CVPR, pp. 1323–1330 (2006)Google Scholar
  6. 6.
    Matusik, W., Pfister, H., Brand, M., McMillan, L.: A data-driven reflectance model. ACM Trans. Graph. 22(3), 759–769 (2003)CrossRefGoogle Scholar
  7. 7.
    Lensch, H.P.A., Lang, J., Sa, A.M., Seidel, H.P., Brunet, P., Fellner, D.W.: Planned sampling of spatially varying BRDFs. In: Proc. Eurographics (2003)Google Scholar
  8. 8.
    Lindner, C., Arigita, J., Puente Leon, F.: Illumination-based segmentation of structured surfaces in automated visual inspection. In: Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series, pp. 99–108 (2005)Google Scholar
  9. 9.
    Wang, O., Gunawardane, P., Scher, S., Davis, J.: Material classification using brdf slices. In: Proc. CVPR (2009)Google Scholar
  10. 10.
    Debevec, P., Hawkins, T., Tchou, C., Duiker, H.P., Sarokin, W., Sagar, M.: Acquiring the reflectance field of a human face. In: SIGGRAPH (2000)Google Scholar
  11. 11.
    Dana, K.: BRDF/BTF measurement device. In: Proc. ICCV (2001)Google Scholar
  12. 12.
    Ghosh, A., Heidrich, W., Achutha, S., O’Toole, M.: BRDF acquisition with basis illumination. In: Proc. ICCV (2007)Google Scholar
  13. 13.
    Robertson, M.A., Borman, S., Stevenson, R.L.: Dynamic range improvement through multiple exposures. In: Proc. ICIP, pp. 159–163 (1999)Google Scholar
  14. 14.
    Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)zbMATHCrossRefGoogle Scholar
  15. 15.
    Bosch, A., Zisserman, A., Munoz, X.: Image classification using random forests and ferns. In: Proc. ICCV, pp. 1–8 (2007)Google Scholar
  16. 16.
    Menze, B.H., Kelm, B.M., Masuch, R., Himmelreich, U., Bachert, P., Petrich, W., Hamprecht, F.A.: A comparison of random forest and its Gini importance with standard chemometric methods for the feature selection and classification of spectral data. BMC Bioinformatics 10, 213 (2009)CrossRefGoogle Scholar
  17. 17.
    Lepetit, V., Fua, P.: Keypoint recognition using randomized trees. PAMI 28(9), 1465–1479 (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Markus Jehle
    • 1
  • Christoph Sommer
    • 1
  • Bernd Jähne
    • 1
  1. 1.Heidelberg Collaboratory for Image Processing (HCI)University of Heidelberg 

Personalised recommendations