Advertisement

Classifying Images of Materials: Achieving Viewpoint and Illumination Independence

  • Manik Varma
  • Andrew Zisserman
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2352)

Abstract

In this paper we present a new approach to material classification under unknown viewpoint and illumination. Our texture model is based on the statistical distribution of clustered filter responses. However, unlike previous 3D texton representations, we use rotationally invariant filters and cluster in an extremely low dimensional space. Having built a texton dictionary, we present a novel method of classifying a single image without requiring any a priori knowledge about the viewing or illumination conditions under which it was photographed. We argue that using rotationally invariant filters while clustering in such a low dimensional space improves classification performance and demonstrate this claim with results on all 61 textures in the Columbia-Utrecht database. We then proceed to show how texture models can be further extended by compensating for viewpoint changes using weak isotropy.

The new clustering and classification methods are compared to those of Leung and Malik (ICCV 1999), Schmid (CVPR 2001) and Cula and Dana (CVPR 2001), which are the current state-of-the-art approaches.

Keywords

Greedy Algorithm Training Image Texture Class Viewpoint Change Photometric Stereo 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    M. J. Chantler, G. McGunnigle, and J. Wu. Surface rotation invariant texture classification using photometric stereo and surface magnitude spectra. In Proc. BMVC., pages 486–495, 2000.Google Scholar
  2. 2.
    O. G. Cula and K. J. Dana. Compact representation of bidirectional texture functions. In Proc. CVPR, 2001.Google Scholar
  3. 3.
    O. G. Cula and K. J. Dana. Recognition methods for 3d textured surfaces. Proceedings of the SPIE, San Jose, Jan 2001.Google Scholar
  4. 4.
    K. Dana and S. Nayar. Histogram model for 3d textures. In Proc. CVPR, pages 618–624, 1998.Google Scholar
  5. 5.
    K. Dana and S. Nayar. Correlation model for 3D texture. In Proc. ICCV, pages 1061–1067, 1999.Google Scholar
  6. 6.
    K. J. Dana, B. van Ginneken, S. K. Nayar, and J. J. Koenderink. Reflectance and texture of real world surfaces. ACM Trans. Graphics, 18,1:1–34, 1999.CrossRefGoogle Scholar
  7. 7.
    R. O. Duda and P. E. Hart. Pattern Classification and Scene Analysis. Wiley, 1973.Google Scholar
  8. 8.
    C. Fowlkes, D. Martin, X. Ren, and J. Malik. Detecting and localizing boundaries in natural images. Technical report, University of California at Berkeley, 2002.Google Scholar
  9. 9.
    G. M. Haley and B. S. Manjunath. Rotation-invariant texture classification using a complete space-frequency model. IEEE PAMI, 8(2):255–269, 1999.Google Scholar
  10. 10.
    L. Kaufman and P. J. Rousseeuw. Finding Groups in Data. John Wiley & Sons, 1990.Google Scholar
  11. 11.
    S. Konishi, A. Yuille, J. Coughlan, and S. Zhu. Fundamental bounds on edge detection: An information theoretic evaluation of different edge cues. In Proc. CVPR, pages 573–579, 1999.Google Scholar
  12. 12.
    S. Konishi and A. L. Yuille. Statistical cues for domain specific image segmentation with performance analysis. In Proc. CVPR, 2000.Google Scholar
  13. 13.
    T. Leung and J. Malik. Representing and recognizing the visual appearance of materials using three-dimensional textons. IJCV, Dec 1999.Google Scholar
  14. 14.
    T. Lindeberg and J. Gårding. Shape-adapted smoothing in estimation of 3-d depth cues from affine distortions of local 2-d brightness structure. In Proc. ECCV, pages 389–400, May 1994.Google Scholar
  15. 15.
    X. Liu, Y. Yu, and H. Shum. Synthesizing bidirectional texture functions for real-world surfaces. In Proc. ACM SIGGRAPH, pages 117–126, 2001.Google Scholar
  16. 16.
    W. Press, B. Flannery, S. Teukolsky, and W. Vetterling. Numerical Recipes in C. Cambridge University Press, 1988.Google Scholar
  17. 17.
    F. Schaffalitzky and A. Zisserman. Viewpoint invariant texture matching and wide baseline stereo. In Proc. ICCV, Jul 2001.Google Scholar
  18. 18.
    C. Schmid. Constructing models for content-based image retrieval. In Proc. CVPR, 2001.Google Scholar
  19. 19.
    A. Zalesny and L. Van Gool. A compact model for viewpoint dependent texture synthesis. volume 2018 of Lecture Notes in Computer Science, pages 124–143. Springer, July 2000.Google Scholar
  20. 20.
    S.C. Zhu, Y. Wu, and D. Mumford. Filters, random-fields and maximum-entropy (FRAME): Towards a unified theory for texture modeling. IJCV, 27(2):107–126, March 1998.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Manik Varma
    • 1
  • Andrew Zisserman
    • 1
  1. 1.Robotics Research Group Department of Engineering ScienceUniversity of OxfordOxford

Personalised recommendations