Skip to main content

Occlusion, Attention and Object Representations

  • Conference paper
Artificial Neural Networks – ICANN 2006 (ICANN 2006)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 4131))

Included in the following conference series:

  • 3412 Accesses

Abstract

Occlusion is currently at the centre of analysis in machine vision. We present an approach to it that uses attention feedback to an occluded object to obtain its correct recognition. Various simulations are performed using a hierarchical visual attention feedback system, based on contrast gain (which we discuss as to its relation to possible hallucinations that could be caused by feedback). We then discuss implications of our results for object representations per se.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Zitnick, C.L., Kanade, T.: A Cooperative Algorithm for Stereo Matching and Occlusion Detection. IEEE Trans. Patt. Anal. Mach. Intel. 22, 675–684 (2000)

    Article  Google Scholar 

  2. Fukushima, K.: Recognition of partly occluded patterns: a neural network model. Biol. Cybern. 84, 251–259 (2001)

    Article  Google Scholar 

  3. Ito, M., Komatsu, H.: Representation of Angles Embedded within Contour Stimuli in Area V2 of Macaque Monkeys. J. Neuroscience 24, 3313–3324 (2004)

    Article  Google Scholar 

  4. Pasupathy, A., Connor, C.E.: Shape Representation in Area V4: Position-Specific Tuning for Boundary Configuration. J. Neurophysiol. 86, 2505–2519 (2001)

    Google Scholar 

  5. Taylor, J.G., Hartley, M., Taylor, N.R.: Attention as Sigma-Pi controlled ACh-based feedback. In: Proc. of IJCNN 2005 (2005)

    Google Scholar 

  6. Lanyon, L.J., Denham, S.L.: A model of active visual search with object-based attention guiding scan paths. Neural Netw. 17, 873–897 (2004)

    Article  MATH  Google Scholar 

  7. van der Velde, F., de Kamps, M.: From Knowing What to Knowing Where: Modeling Object-Based Attention with Feedback Disinhibition of Activation. J. Cog. Neurosci. 13, 479–491 (2001)

    Article  Google Scholar 

  8. Reynolds, J.H., Chelazzi, L., Desimone, R.: Competitive mechanisms subserve attention in Macaque areas V2 and V4. J. Neurosci. 19, 1736–1753 (1999)

    Google Scholar 

  9. Taylor, J.G., Rogers, M.: A control model of the movement of attention. Neural Netw. 15, 309–326 (2002)

    Article  Google Scholar 

  10. Taylor, N.R., Hartley, M., Taylor, J.G.: The Micro-Structure of Attention (2006) (accepted for CNS 2006)

    Google Scholar 

  11. Taylor, N.R., Hartley, M., Taylor, J.G.: Analysing Attention at Neuron level (2006) (accepted for BICS 2006)

    Google Scholar 

  12. Grossberg, S., Raizada, R.D.: Contrast-sensitive perceptual grouping and object-based attention in the laminar circuits of primary visual cortex. Vision Res. 40, 1413–1432 (2000)

    Article  Google Scholar 

  13. Deco, G., Rolls, E.T.: Neurodynamics of biased competition and cooperation for attention: a model with spiking neurons. J. Neurophysiol. 94, 295–313 (2005)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2006 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Taylor, N.R., Panchev, C., Hartley, M., Kasderidis, S., Taylor, J.G. (2006). Occlusion, Attention and Object Representations. In: Kollias, S.D., Stafylopatis, A., Duch, W., Oja, E. (eds) Artificial Neural Networks – ICANN 2006. ICANN 2006. Lecture Notes in Computer Science, vol 4131. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11840817_62

Download citation

  • DOI: https://doi.org/10.1007/11840817_62

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-38625-4

  • Online ISBN: 978-3-540-38627-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics