A Cascade of Unsupervised and Supervised Neural Networks for Natural Image Classification

  • Julien Ros
  • Christophe Laurent
  • Grégoire Lefebvre
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4071)


This paper presents an architecture well suited for natural image classification or visual object recognition applications. The image content is described by a distribution of local prototype features obtained by projecting local signatures on a self-organizing map. The local signatures describe singularities around interest points detected by a wavelet-based salient points detector. Finally, images are classified by using a multilayer perceptron receiving local prototypes distribution as input. This architecture obtains good results both in terms of global classification rates and computing times on different well known datasets.


Support Vector Machine Radial Basis Function Area Under Curve Interest Point Query Image 
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.
    Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, 2nd edn. John Wiley & Sons, Chichester (2001)MATHGoogle Scholar
  2. 2.
    Schmid, C., Mohr, R.: Local grayvalue invariants for image retrieval. IEEE Transaction on Pattern Analysis and Machine Intelligence 19(5), 530–535 (1997)CrossRefGoogle Scholar
  3. 3.
    Csurka, G., Bray, C., Dance, C., Fan, L.: Visual categorization with bags of keypoints. In: The 8th European Conference on Computer Vision, Prague, Czech Republic, pp. 327–334 (2004)Google Scholar
  4. 4.
    Jurie, F., Triggs, B.: Creating efficient codebooks for visual recognition. In: International Conference on Computer Vision, Beijing, China, pp. 604–610 (2005)Google Scholar
  5. 5.
    Weber, M., Welling, M., Perona, P.: Unsupervised learning of models for recognition. In: The 6th European Conference on Computer Vision, London, UK, pp. 18–32. Springer, Heidelberg (2000)Google Scholar
  6. 6.
    Fei-Fei, L., Perona, P.: A hierarchical bayesian model for learning natural scene categories. In: International Conference on Computer Vision and Pattern Recognition, San Diego, CA, USA, vol. 2, pp. 524–531 (2005)Google Scholar
  7. 7.
    Marée, R., Geurts, P., Piater, J., Wehenkel, L.: Random subwindows for robust image classification. In: International Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 34–40 (2005)Google Scholar
  8. 8.
    Agarwal, S., Awan, A., Roth, D.: Learning to detect objects in images via a sparse, part-based representation. IEEE Transactions on Pattern Analysis and Machine Intelligence 26(11), 1475–1490 (2004)CrossRefGoogle Scholar
  9. 9.
    Kohonen, T.: Self-Organizing Maps. Springer, Heidelberg (2001)MATHGoogle Scholar
  10. 10.
    Laurent, C., Laurent, N., Maurizot, M., Dorval, T.: In depth analysis and evaluation of saliency-based color image indexing methods using wavelet salient features. In: Multimedia Tools and Application (2004)Google Scholar
  11. 11.
    Bres, S., Jolion, J.M.: Detection of interest points for image indexation. In: 3rd International Conference on Visual Information Systems, Amsterdam, The Netherlands, pp. 427–434 (1999)Google Scholar
  12. 12.
    Harris, C., Stephens, M.: A combined corner and edge detector. In: 4th Alvey Vision Conference, pp. 147–151 (1988)Google Scholar
  13. 13.
    Mikolajczyk, K., Schmid, C.: Scale and affine invariant interest point detectors. International Journal of Computer Vision 60(1), 63–86 (2004)CrossRefGoogle Scholar
  14. 14.
    Loupias, E., Sebe, N., Bres, S., Jolion, J.M.: Wavelet-based salient points for image retrieval. In: IEEE International Conference on Image Processing, Vancouver, Canada, pp. 518–521 (2000)Google Scholar
  15. 15.
    Mallat, S.: Foveal Approximations for Singularities. Applied and Computational Harmonic Analysis 14(2), 133–180 (2003)MATHCrossRefMathSciNetGoogle Scholar
  16. 16.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60(2), 91–110 (2004)CrossRefGoogle Scholar
  17. 17.
    Rauber, A., Merkl, D., Dittenbach, M.: The growing hierarchical self-organizing maps: Exploratory analysis of high-dimensional data. IEEE Transactions on Neural Networks 13(6), 1331–1341 (2002)CrossRefGoogle Scholar
  18. 18.
    Hagenbuchner, M., Sperduti, A.: A self-organizing map for adaptive processing of structured data. IEEE Transactions on Neural Networks 14(3), 491–505 (2003)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Julien Ros
    • 1
  • Christophe Laurent
    • 1
  • Grégoire Lefebvre
    • 1
  1. 1.TECH/IRIS/CIMFrance Télécom R&DCesson SévignéFrance

Personalised recommendations