BIO-INSPIRED BAGS-OF-FEATURES FOR IMAGE CLASSIFICATION

Wafa Bel Haj Ali, Eric Debreuve, Pierre Kornprobst, Michel Barlaud

2011

Abstract

The challenge of image classification is based on two key elements: the image representation and the algorithm of classification. In this paper, we revisited the topic of image representation. Classical descriptors such as Bag-of-Features are usually based on SIFT. We propose here an alternative based on bio-inspired features. This approach is inspired by a model of the retina which acts as an image filter to detect local contrasts. We show the promising results that we obtained in natural scenes classification with the proposed bio-inspired image representation.

References

  1. Bel Haj Ali, W., Piro, P., Debreuve, E., and Barlaud, M. (2010). From descriptor to boosting: Optimizing the k-nn classification rule. In Content-Based Multimedia Indexing (CBMI), 2010 International Workshop on, pages 1-5.
  2. Cortes, C. and Vapnik, V. (1995). Support-vector networks. Machine Learning, 20:273-297. 10.1007/ BF00994018.
  3. Delorme, A., Gautrais, J., van Rullen, R., and Thorpe, S. (1999). Spikenet: A simulator for modeling large networks of integrate and fire neurons. Neurocomputing, 26-27:989-996.
  4. Denoeux, T. (1995). A k-nearest neighbor classification rule based on dempster-shafer theory. Systems, Man and Cybernetics, IEEE Transactions on, 25(5):804-813.
  5. Escobar, M.-J., Masson, G., Vieville, T., and Kornprobst, P. (2009). Action recognition using a bio-inspired feedforward spiking network. International Journal of Computer Vision, 82:284-301. 10.1007/s11263-008- 0201-1.
  6. Field, D. J. (1994). What is the goal of sensory coding? Neural Computation, 6(4):559-601.
  7. Freund, Y. and Schapire, R. E. (1995). A decision-theoretic generalization of on-line learning and an application to boosting.
  8. Lazebnik, S., Schmid, C., and Ponce, J. (2006). Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In IEEE Conference on Computer Vision and Pattern Recognition, New York (NY), USA.
  9. Lowe, D. G. (1999). Object recognition from local scaleinvariant features. Computer Vision, IEEE International Conference on, 2:1150.
  10. Oliva, A. and Torralba, A. (2001). Modeling the shape of the scene: A holistic representation of the spatial envelope. International Journal of Computer Vision, 42:145-175. 10.1023/A:1011139631724.
  11. Piro, P., Nock, R., Nielsen, F., and Barlaud, M. (2010). Boosting k-nn for categorization of natural scenes. ArXiv e-prints.
  12. Rodieck, R. (1965). Quantitative analysis of cat retinal ganglion cell response to visual stimuli. Vision Research, 5(12):583-601.
  13. Russell, B., Torralba, A., Murphy, K., and Freeman, W. (2008). Labelme: A database and web-based tool for image annotation. International Journal of Computer Vision, 77:157-173. 10.1007/s11263-007-0090-8.
  14. Schapire, R. E. and Singer, Y. (1999). Improved boosting algorithms using confidence-rated predictions. Machine Learning, 37:297-336. 10.1023/A:1007614523901.
  15. Sivic, J. and Zisserman, A. (2006). Video google: Efficient visual search of videos. In Ponce, J., Hebert, M., Schmid, C., and Zisserman, A., editors, Toward Category-Level Object Recognition, volume 4170 of Lecture Notes in Computer Science, pages 127-144. Springer Berlin / Heidelberg. 10.1007/11957959 7.
  16. Thorpe, S. and Gautrais, J. (1998). Rank order coding. In Proceedings of the sixth annual conference on Computational neuroscience : trends in research, 1998: trends in research, 1998, CNS 7897, pages 113-118, New York, NY, USA. Plenum Press.
  17. Thorpe, S. J., Guyonneau, R., Guilbaud, N., Allegraud, J.- M., and VanRullen, R. (2004). Spikenet: real-time visual processing with one spike per neuron. Neurocomputing, 58-60:857-864. Computational Neuroscience: Trends in Research 2004.
  18. Van Rullen, R. and Thorpe, S. J. (2001). Rate coding versus temporal order coding: what the retinal ganglion cells tell the visual cortex. Neural Comput, 13(6):1255- 1283.
  19. Vedaldi, A. and Fulkerson, B. (2008). VLFeat: An open and portable library of computer vision algorithms. http:// www.vlfeat.org/.
Download


Paper Citation


in Harvard Style

Bel Haj Ali W., Debreuve E., Kornprobst P. and Barlaud M. (2011). BIO-INSPIRED BAGS-OF-FEATURES FOR IMAGE CLASSIFICATION . In Proceedings of the International Conference on Knowledge Discovery and Information Retrieval - Volume 1: KDIR, (IC3K 2011) ISBN 978-989-8425-79-9, pages 269-273. DOI: 10.5220/0003663402770281


in Bibtex Style

@conference{kdir11,
author={Wafa Bel Haj Ali and Eric Debreuve and Pierre Kornprobst and Michel Barlaud},
title={BIO-INSPIRED BAGS-OF-FEATURES FOR IMAGE CLASSIFICATION},
booktitle={Proceedings of the International Conference on Knowledge Discovery and Information Retrieval - Volume 1: KDIR, (IC3K 2011)},
year={2011},
pages={269-273},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003663402770281},
isbn={978-989-8425-79-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Knowledge Discovery and Information Retrieval - Volume 1: KDIR, (IC3K 2011)
TI - BIO-INSPIRED BAGS-OF-FEATURES FOR IMAGE CLASSIFICATION
SN - 978-989-8425-79-9
AU - Bel Haj Ali W.
AU - Debreuve E.
AU - Kornprobst P.
AU - Barlaud M.
PY - 2011
SP - 269
EP - 273
DO - 10.5220/0003663402770281