Ensembles of novel visual keywords descriptors for image categorization

  title={Ensembles of novel visual keywords descriptors for image categorization},
  author={Azizi Abdullah and Remco C. Veltkamp and Marco Wiering},
  journal={2010 11th International Conference on Control Automation Robotics & Vision},
Object recognition systems need effective image descriptors to obtain good performance levels. Currently, the most widely used image descriptor is the SIFT descriptor that computes histograms of orientation gradients around points in an image. A possible problem of this approach is that the number of features becomes very large when a dense grid is used where the histograms are computed and combined for many different points. The current dominating solution to this problem is to use a… CONTINUE READING
Highly Cited
This paper has 19 citations. REVIEW CITATIONS


Publications referenced by this paper.
Showing 1-10 of 19 references

Comparison between product and mean classifier combination rules

  • D. M. Tax, R. P. Duin, M. V. Breukelen
  • Proceedings of the Workshop on Statistical…
  • 1997
Highly Influential
4 Excerpts

Similar Papers

Loading similar papers…