Object Localization by Subspace Clustering of Local Descriptors

  • C. Bouveyron
  • J. Kannala
  • C. Schmid
  • S. Girard
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4338)


This paper presents a probabilistic approach for object localization which combines subspace clustering with the selection of discriminative clusters. Clustering is often a key step in object recognition and is penalized by the high dimensionality of the descriptors. Indeed, local descriptors, such as SIFT, which have shown excellent results in recognition, are high-dimensional and live in different low-dimensional subspaces. We therefore use a subspace clustering method called High-Dimensional Data Clustering (HDDC) which overcomes the curse of dimensionality. Furthermore, in many cases only a few of the clusters are useful to discriminate the object. We, thus, evaluate the discriminative capacity of clusters and use it to compute the probability that a local descriptor belongs to the object. Experimental results demonstrate the effectiveness of our probabilistic approach for object localization and show that subspace clustering gives better results compared to standard clustering methods. Furthermore, our approach outperforms existing results for the Pascal 2005 dataset.


Gaussian Mixture Model Interest Point Object Localization Local Descriptor Subspace Cluster 
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.
    Agarwal, S., Roth, D.: Learning a sparse representation for object detection. In: 7th European Conference on Computer Vision, vol. 4, pp. 113–130 (2002)Google Scholar
  2. 2.
    Dorko, G., Schmid, C.: Object class recognition using discriminative local features. Technical Report 5497, INRIA (2004)Google Scholar
  3. 3.
    Leibe, B., Schiele, B.: Interleaved object categorization and segmentation. In: British Machine Vision Conference, Norwich, England (2003)Google Scholar
  4. 4.
    Willamowski, J., Arregui, D., Csurka, G., Dance, C., Fan, L.: Coategorizing nine visual classes using local appareance descriptors. In: International Workshop on Learning for Adaptable Visual Systems, Cambridge, UK (2004)Google Scholar
  5. 5.
    Zhang, J., Marszalek, M., Lazebnik, S., Schmid, C.: Local features and kernels for classification of texture and object categories. Technical report, INRIA (2005)Google Scholar
  6. 6.
    Sivic, J., Russell, B., Efros, A., Zisserman, A., Freeman, W.: Discovering objects and their location in images. In: International Conference on Computer Vision (2005)Google Scholar
  7. 7.
    Opelt, A., Fussenegger, M., Pinz, A., Auer, P.: Weak hypotheses and boosting for generic object detection and recognition. In: European Conference on Computer Vision, vol. 2, pp. 71–84 (2004)Google Scholar
  8. 8.
    McLachlan, G., Peel, D.: Finite Mixture Models. Wiley Interscience, New York (2000)MATHCrossRefGoogle Scholar
  9. 9.
    Jolliffe, I.: Principal Component Analysis. Springer, New York (1986)Google Scholar
  10. 10.
    Schölkopf, B., Smola, A., Müller, K.: Nonlinear component analysis as a kernel eigenvalue problem. Neural Computation 10, 1299–1319 (1998)CrossRefGoogle Scholar
  11. 11.
    Guyon, I., Elisseeff, A.: An introduction to variable and feature selection. Journal of Machine Learning Research 3, 1157–1182 (2003)MATHCrossRefGoogle Scholar
  12. 12.
    Fraley, C., Raftery, A.: Model-based clustering, discriminant analysis and density estimation. Journal of American Statistical Association 97, 611–631 (2002)MATHCrossRefMathSciNetGoogle Scholar
  13. 13.
    Parsons, L., Haque, E., Liu, H.: Subspace clustering for high dimensional data: a review. SIGKDD Explor. Newsl. 6, 90–105 (2004)CrossRefGoogle Scholar
  14. 14.
    Tipping, M., Bishop, C.: Mixtures of probabilistic principal component analysers. Neural Computation 11, 443–482 (1999)CrossRefGoogle Scholar
  15. 15.
    Moghaddam, B.: Principal Manifolds and Probabilistic Subspaces for Visual Recognition. IEEE Trans. on Pattern Analysis and Machine Intelligence 24, 780–788 (2002)CrossRefGoogle Scholar
  16. 16.
    Bouveyron, C., Girard, S., Schmid, C.: High-Dimensional Data Clustering. Technical Report 1083M, LMC-IMAG, Université J. Fourier Grenoble 1 (2006)Google Scholar
  17. 17.
    Everingham, M., Zisserman, A., Williams, C., Gool, L.V., et al.: The 2005 PASCAL visual object classes challenge. In: First PASCAL Challenge Workshop, Springer, Heidelberg (2006)Google Scholar
  18. 18.
    Cattell, R.: The scree test for the number of factors. Multivariate Behavioral Research 1, 245–276 (1966)CrossRefGoogle Scholar
  19. 19.
    Mikolajczyk, K., Schmid, C.: Scale and affine invariant interest point detectors. International Journal of Computer Vision 60, 63–86 (2004)CrossRefGoogle Scholar
  20. 20.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60, 91–110 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • C. Bouveyron
    • 1
  • J. Kannala
    • 2
  • C. Schmid
    • 1
  • S. Girard
    • 1
  1. 1.INRIA Rhône-AlpesSaint-IsmierFrance
  2. 2.Machine Vision Group, dept. of Electrical and Information EngineeringUniversity of OuluFinland

Personalised recommendations