Neural Object Recognition by Hierarchical Learning and Extraction of Essential Shapes

  • Daniel Oberhoff
  • Marina Kolesnik
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4729)


We present a hierarchical system for object recognition that models neural mechanisms of visual processing identified in the mammalian ventral stream. The system is composed of neural units organized in a hierarchy of layers with increasing complexity. A key feature of the system is that the neural units learn their preferred patterns from visual input alone. Through this “soft wiring” of neural units the system becomes tuned for target object classes through pure visual experience and with no prior labeling. Object labels are only introduced to train a classifier on the system’s output. The system’s tuning takes place in a feed-forward path. We also present a neural mechanism for back projection of the learned image patterns down the hierarchical layers. This feedback mechanism could serve as a starting point for integration of what- and where-information processed by the ventral and dorsal stream. We test the neural system with natural images from publicly available datasets of natural scenes and handwritten digits.


Object Recognition Recognition Rate Dorsal Stream Ventral Stream Handwritten Digit 
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.
    Ungerleider, L.G., Mishkin, M.: Two cortical visual systems. In: Analysis of Visual Behavior, pp. 549–586. MIT Press, Cambridge (1992)Google Scholar
  2. 2.
    Hung, C.P., Kreiman, G., Poggio, T., DiCarlo, J.J.: Fast readout of object identity from macaque inferior temporal cortex. Science Reports (2005)Google Scholar
  3. 3.
    Hubel, D.H., Wiesel, T.N.: Receptive fields and functional architecture of monkey striate cortex. J. Physiol. 195 (1967)Google Scholar
  4. 4.
    Fukushima, K.: Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cyb. V36(4), 193–202 (1980)CrossRefGoogle Scholar
  5. 5.
    LeCun, Y., Jackel, L.D., Boser, B., Denker, J.S., Graf, H.P., Guyon, I., Henderson, D., Howard, R.E., Hubbard, W.: Handwritten digit recognition: Applications of neural net chips and automatic learning. IEEE Comm., 41–46 (invited paper, 1989)Google Scholar
  6. 6.
    Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: Proc. CVPR, IEEE Press, Los Alamitos (2006)Google Scholar
  7. 7.
    Serre, T., Kouh, M., Cadieu, C., Knoblich, U., Kreiman, G., Poggio, T.: A theory of object recognition: Computations and circuits in the feedforward path of the ventral stream in primate visual cortex. CBCL Memo 259 (2005)Google Scholar
  8. 8.
    Deco, G., Rolls, E.T.: A neurodynamical cortical model of visual attention and invariant object recognition. Vis. Res. 44 (2004)Google Scholar
  9. 9.
    Rolls, E.T., Deco, G.: The Computational Neuroscience of Vision. Oxford University Press, Oxford (2002)Google Scholar
  10. 10.
    Felleman, D.J., Van Essen, D.C.: Distributed Hierarchical Processing in the Primate Cerebral Cortex. Cereb. Cortex 1, 1–a–47 (1991)Google Scholar
  11. 11.
    Tsotsos, J.K., Culhane, S.M., Wai, W.Y.K., Lai, Y., Davis, N., Nuflo, F.: Modeling visual attention via selective tuning. Artificial Intelligence 78, 507–545 (1994)CrossRefGoogle Scholar
  12. 12.
    Mutch, J., Lowe, D.G.: Multiclass object recognition with sparse, localized features. In: Proc. CVPR, pp. 11–18 (2006)Google Scholar
  13. 13.
    Munder, S., Gavrila, D.M.: An experimental study on pedestrian classification. IEEE Trans. Pattern Analysis and Machine Intelligence 28, 1863–1868 (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Daniel Oberhoff
    • 1
  • Marina Kolesnik
    • 1
  1. 1.Fraunhofer Institut FIT, Schloss Birlinghoven, 53754 Sankt Augustin 

Personalised recommendations