Advertisement

On the Significance of Real-World Conditions for Material Classification

  • Eric Hayman
  • Barbara Caputo
  • Mario Fritz
  • Jan-Olof Eklundh
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3024)

Abstract

Classifying materials from their appearance is a challenging problem, especially if illumination and pose conditions are permitted to change: highlights and shadows caused by 3D structure can radically alter a sample’s visual texture. Despite these difficulties, researchers have demonstrated impressive results on the CUReT database which contains many images of 61 materials under different conditions. A first contribution of this paper is to further advance the state-of-the-art by applying Support Vector Machines to this problem. To our knowledge, we record the best results to date on the CUReT database.

In our work we additionally investigate the effect of scale since robustness to viewing distance and zoom settings is crucial in many real-world situations. Indeed, a material’s appearance can vary considerably as fine-level detail becomes visible or disappears as the camera moves towards or away from the subject. We handle scale-variations using a pure-learning approach, incorporating samples imaged at different distances into the training set. An empirical investigation is conducted to show how the classification accuracy decreases as less scale information is made available during training. Since the CUReT database contains little scale variation, we introduce a new database which images ten CUReT materials at different distances, while also maintaining some change in pose and illumination. The first aim of the database is thus to provide scale variations, but a second and equally important objective is to attempt to recognise different samples of the CUReT materials. For instance, does training on the CUReT database enable recognition of another piece of sandpaper? The results clearly demonstrate that it is not possible to do so with any acceptable degree of accuracy. Thus we conclude that impressive results even on a well-designed database such as CUReT, does not imply that material classification is close to being a solved problem under real-world conditions.

Keywords

Support Vector Machine Radial Basis Function Recognition Rate Markov Random Field Image Patch 
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.
    Avidan, S.: Support vector tracking. In: Proc. CVPR, Kauai, Hawaii, pp. 1:184–191 (2001)Google Scholar
  2. 2.
    Barla, A., Odone, F., Verri, A.: Hausdorff kernel for 3D object acquisition and detection. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2353, pp. 20–33. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  3. 3.
    Belongie, S., Fowlkes, C.C., Chung, F., Malik, J.: Spectral partitioning with indefinite kernels using the Nystrcim extension. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. III: 531–542. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  4. 4.
    Brodatz, P.: Textures. Dover, New York (1966)Google Scholar
  5. 5.
    Caputo, B., Dorko, G.: How to combine color and shape information for 3D object recognition: kernels do the trick. In: Proc. NIPS, Vancouver (2002)Google Scholar
  6. 6.
    Chang, C.-C., Lin, C.-J.: LIBSVM: a library for support vector machines (2001), Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm
  7. 7.
    Chapelle, O., Haffner, P., Vapnik, V.: SVMs for histogram-based image classification. IEEE Trans. on Neural Networks 10(5) (1999)Google Scholar
  8. 8.
    Cristianini, N., Taylor, J.S.: An introduction to support vector machines and other kernel-based learning methods. Cambridge University Press, Cambridge (2000)Google Scholar
  9. 9.
    Cula, O.G., Dana, K.J.: Compact representation of bidirectional texture functions. In: Proc. CVPR, Kauai, Hawaii, pp. 1:1041–1047 (2001)Google Scholar
  10. 10.
    Dana, K.J., van Ginneken, B., Nayar, S.K., Koenderink, J.J.: Reflectance and texture of real-world surfaces. ACM Transactions on Graphics 18(1), 1–34 (1999)CrossRefGoogle Scholar
  11. 11.
    Efros, A., Leung, T.: Texture synthesis by non-parametric sampling. In: Proc. ICCV, Kerkyra, Greece, pp. 1033–1038 (1999)Google Scholar
  12. 12.
    Fritz, M., Hayman, E., Caputo, B., Eklundh, J.-O.: The KTH-TIPS database, Available at http://www.nada.kth.se/cvap/databases/kth-tips
  13. 13.
    Julesz, B., Bergen, R.: Textons, the elements of texture perception, and their interactions. Nature 290, 91–97 (1981)CrossRefGoogle Scholar
  14. 14.
    Kim, K.I., Jung, K., Park, S.H., Kim, H.J.: Support vector machines for texture classification. PAMI 24(11), 1542–1550 (2002)Google Scholar
  15. 15.
    Lazebnik, S., Schmid, C., Ponce, J.: Affine-invariant local descriptors and neighbourhood statistics for texture recognition. In: Proc. ICCV, Nice, pp. 649–655 (2003)Google Scholar
  16. 16.
    Leung, T., Malik, J.: Representing and recognizing the visual appearance of materials using three-dimensional textons. IJCV 43(1), 29–44 (2001)zbMATHCrossRefGoogle Scholar
  17. 17.
    Li, S.Z., Fu, Q.D., Gu, L., Scholkopf, B., Cheng, Y., Zhang, H.J.: Kernel machine based learning for multi-view face detection and pose estimation. In: Proc. ICCV, Vancouver, pp. II: 674–679 (2001)Google Scholar
  18. 18.
    Lindeberg, T.: Feature detection with automatic scale selection. IJCV 30(2), 79–116 (1998)CrossRefGoogle Scholar
  19. 19.
    Mäenpää, T., Pietikäinen, M.: Multi-scale binary patterns for texture analysis. In: Bigun, J., Gustavsson, T. (eds.) SCIA 2003. LNCS, vol. 2749, pp. 885–892. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  20. 20.
    Malik, J., Belongie, S., Shi, J., Leung, T.: Textons, contours and regions: Cue integration in image segmentation. In: Proc. ICCV, Kerkyra, Greece, pp. 918–925 (1999)Google Scholar
  21. 21.
    Manjunath, B.S., Ma, W.Y.: Texture features for browsing and retrieval of image data. PAMI 18(8), 837–842 (1996)Google Scholar
  22. 22.
    Manthalkar, R., Biswas, P.K., Chatterji, B.N.: Rotation and scale invariant texture classification using gabor wavelets. In: Texture Workshop, pp. 87–90 (2002)Google Scholar
  23. 23.
    Ojala, T., Pietikäainen, M., Harwood, D.: A comparative study of texture measures with classification based on feature distributions. PR 29(1), 51–59 (1996)Google Scholar
  24. 24.
    Penirschke, A., Chantler, M.J., Petrou, M.: Illuminant rotation invariant classification of 3D surface textures using Lissajous’s ellipses. In: Texture Workshop, pp. 103–108 (2002)Google Scholar
  25. 25.
    Platt, J.C., Cristianini, N., Shawe-Taylor, J.: Large margin DAGs for multiclass classification. In: Proc. NIPS 2000, Denver, Colorado (2000)Google Scholar
  26. 26.
    Pontil, M., Verri, A.: Support vector machines for 3D object recognition. PAMI 20(6), 637–646 (1998)Google Scholar
  27. 27.
    Roobaert, D., Zillich, M., Eklundh, J.O.: A pure learning approach to background-invariant object recognition using pedagogical support vector learning. In: Proc. CVPR, Kauai, Hawaii, pp. II: 351–357 (2001)Google Scholar
  28. 28.
    Singh, S., Haddon, J., Markou, M.: Nearest-neighbour classifiers in natural scene analysis. PR 34(8), 1601–1612 (2001)zbMATHGoogle Scholar
  29. 29.
    Vapnik, V.: Statistical learning theory. Wiley and Son, New York (1998)zbMATHGoogle Scholar
  30. 30.
    Varma, M.: Private communication (2003)Google Scholar
  31. 31.
    Varma, M., Zisserman, A.: Classifying images of materials: Achieving viewpoint and illumination independence. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. III: 255–271. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  32. 32.
    Varma, M., Zisserman, A.: Texture classification: are filter banks necessary? In: Proc. CVPR, Madison, Wisconsin, pp. II: 691–698 (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Eric Hayman
    • 1
  • Barbara Caputo
    • 1
  • Mario Fritz
    • 1
  • Jan-Olof Eklundh
    • 1
  1. 1.Computational Vision and Active Perception Laboratory, Dept. of Numerical Analysis and Computer ScienceRoyal Institute of Technology (KTH)StockholmSweden

Personalised recommendations