The problem of learning the class identity of visual objects has received considerable attention recently. With rare exception, all of the work to date assumes low variation in appearance, which limits them to a single depictive style usually photographic. The same object depicted in other styles — as a drawing, perhaps — cannot be identified reliably. Yet humans are able to name the object no matter how it is depicted, and even recognise a real object having previously seen only a drawing.

This paper describes a classifier which is unique in being able to learn class identity no matter how the class instances are depicted. The key to this is our proposition that topological structure is a class invariant. Practically, we depend on spectral graph analysis of a hierarchical description of an image to construct a feature vector of fixed dimension. Hence structure is transformed to a feature vector, which can be classified using standard methods. We demonstrate the classifier on several diverse classes.


Feature Vector Adjacency Matrix Gaussian Mixture Model Spectral Graph Theory Graph Energy 
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.


  1. 1.
    Ahuja, N., Todorovic, S.: Discovering hierarchical taxonomy of categories and shared subcategories in images. In: ICCV (2007)Google Scholar
  2. 2.
    Leibe, B., Schiele, B.: Interleaved object categorization and segmentation. In: BMVCGoogle Scholar
  3. 3.
    Andrew Bangham, J., Moravoc, K., Harvey, R., Fisher, M.: Scale-space trees and applications as filters, for stereo vision and image retrieval. In: Pridmore, T., Elliman, D. (eds.) British Machine Vision Conference (August 1999)Google Scholar
  4. 4.
    Chung, F.R.K.: Spectral graph theory. American Mathematical Society (1997)Google Scholar
  5. 5.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 1, 91–110 (2004)CrossRefGoogle Scholar
  6. 6.
    Fidler, S., Leonardis, A.: Towards scalable representations of object categories: Learning a hierarchy of parts. In: ICCV (2007)Google Scholar
  7. 7.
    Schroff, F., Criminisi, A., Zisserman, A.: Havesting image databases from the web. In: ICCV (2007)Google Scholar
  8. 8.
    Grauman, K., Darrell, T.: Unsupervised learning of catagories from sets of partially matching image features. In: CVPR (2006)Google Scholar
  9. 9.
    Gutman, I., Zhou, B.: Laplacian energy of a graph. Linear Algebra and its Applications 44, 29–37 (2006)MathSciNetCrossRefzbMATHGoogle Scholar
  10. 10.
    Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. TPAMI 2005 27(10), 1615–1630 (2005)Google Scholar
  11. 11.
    Fei-Fei, L., Fergus, R., Perona, P.: A bayesian approach to unsupervised one-shot learning. In: ICCV (2003)Google Scholar
  12. 12.
    Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. In: BMVC (2002)Google Scholar
  13. 13.
    Mikolajczyk, K., Leibe, B., Schiele, B.: Multiple object class detection with a generative model. In: CVPR (2006)Google Scholar
  14. 14.
    Mutch, J., Lowe, D.: Multiclass object recognition with sparse, localized features. In: CVPR (2006)Google Scholar
  15. 15.
    Pinz, A., Opelt, A., Zisserman, A.: A boundary-fragment-model for object detection. In: ECCV (2006)Google Scholar
  16. 16.
    Yan, P., Khan, S.M., Shah, M.: 3d model based object detection in an arbitrary view. In: ICCV (2007)Google Scholar
  17. 17.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. In: International Conference on Computer Vision and Pattern Recognition (1997)Google Scholar
  18. 18.
    Schechtman, S., Irani, M.: Matching local self-similarities across images and videos. In: CVPR (2007)Google Scholar
  19. 19.
    Weber, M., Welling, M., Perona, P.: Unsupervised learning of models for visual object class recognitionGoogle Scholar
  20. 20.
    Zhu, P., Wilson, R.C.: Stability of the eigenvalues of graphs. In: Gagalowicz, A., Philips, W. (eds.) CAIP 2005. LNCS, vol. 3691, pp. 371–378. Springer, Heidelberg (2005)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Bai Xiao
    • 1
  • Yi-Zhe Song
    • 1
  • Anupriya Balika
    • 1
  • Peter M. Hall
    • 1
  1. 1.Computer Science DepartmentUniversity of BathU.K.

Personalised recommendations