Combining Local Feature Histograms of Different Granularities

  • Ville Viitaniemi
  • Jorma Laaksonen
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5575)

Abstract

Histograms of local features have proven to be powerful representations in image category detection. Histograms with different numbers of bins encode the visual information with different granularities. In this paper we experimentally compare techniques for combining different granularities in a way that the resulting descriptors can be used as feature vectors in conventional vector space learning algorithms. In particular, we consider two main approaches: fusing the granularities on SVM kernel level and moving away from binary or hard to soft histograms. We find soft histograms to be a more effective approach, resulting in substantial performance improvement over single-granularity histograms.

Keywords

Interest Point Codebook Size Histogram Intersection Speedup Structure Codebook Vector 
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.

References

  1. 1.
    Madigan, D., Genkin, A., Lewis, D.D.: BBR: Bayesian logistic regression software (2005), http://www.stat.rutgers.edu/~madigan/BBR/
  2. 2.
    Chang, C., Lin, C.: LIBSVM: a library for support vector machines (2001), http://www.csie.ntu.edu.tw/~cjlin/libsvm
  3. 3.
    Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2007 (VOC 2007) (2007), http://www.pascal-network.org/challenges/VOC/voc2007/workshop/index.html
  4. 4.
    Grauman, K., Darrell, T.: The pyramid match kernel: Efficient learning with sets of features. Journal of Machine Learning Research (2007)Google Scholar
  5. 5.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60(2), 91–110 (2004)CrossRefGoogle Scholar
  6. 6.
    Mikolajcyk, K., Schmid, C.: Scale and affine point invariant interest point detectors. International Journal of Computer Vision 60(1), 68–86 (2004)Google Scholar
  7. 7.
    Viitaniemi, V., Laaksonen, J.: Improving the accuracy of global feature fusion based image categorisation. In: Falcidieno, B., Spagnuolo, M., Avrithis, Y., Kompatsiaris, I., Buitelaar, P. (eds.) SAMT 2007. LNCS, vol. 4816, pp. 1–14. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  8. 8.
    Viitaniemi, V., Laaksonen, J.: Experiments on selection of codebooks for local image feature histograms. In: Sebillo, M., Vitiello, G., Schaefer, G. (eds.) VISUAL 2008. LNCS, vol. 5188, pp. 126–137. Springer, Heidelberg (2008)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Ville Viitaniemi
    • 1
  • Jorma Laaksonen
    • 1
  1. 1.Department of Information and Computer ScienceHelsinki University of TechnologyTKKFinland

Personalised recommendations