DIFFERENCE OF GAUSSIANS TYPE NEURAL IMAGE FILTERING WITH SPIKING NEURONS

Sylvain Chevallier, Sonia Dahdouh

2009

Abstract

This contribution describes a bio-inspired image filtering method using spiking neurons. Bio-inspired approaches aim at identifying key properties of biological systems or models and proposing efficient implementations of these properties. The neural image filtering method takes advantage of the temporal integration behavior of spiking neurons. Two experimental validations are conducted to demonstrate the interests of this neural-based method. The first set of experiments compares the noise resistance of a convolutional difference of Gaussians (DOG) filtering method and the neuronal DOG method on a synthetic image. The other experiment explores the edges recovery ability on a natural image. The results show that the neural-based DOG filtering method is more resistant to noise and provides a better edge preservation than classical DOG filtering method.

References

  1. Abbott, L. (1999). Lapicque's introduction of the integrateand-fire model neuron (1907). Brain Research Bulletin, 50(5-6):303-304.
  2. Ahrns, I. and Neumann, H. (1999). Space-variant dynamic neural fields for visual attention. In Int. Conf. on Computer Vision and Pattern Recognition (CVPR), volume 2, page 318. IEEE Computer Society.
  3. Chevallier, S. and Tarroux, P. (2008). Covert attention with a spiking neural network. In Gasteratos, A., Vincze, M., and Tsotsos, J., editors, Int. Conf. on Computer Vision Systems (ICVS), volume 5008 of Lecture Notes in Computer Science, pages 56-65. Springer.
  4. Chevallier, S., Tarroux, P., and Paugam-Moisy, H. (2006). Saliency extraction with a distributed spiking neural network. In Verleysen, M., editor, European Symposium on Artificial Neural Networks (ESANN), pages 209-214, Bruges, Belgium.
  5. de Brecht, M. and Saiki, J. (2006). A neural network implementation of a saliency map model. Neural Networks, 19(10):1467-1474.
  6. Enroth-Cugell, C. and Robson, J. (1966). The contrast sensitivity of retinal ganglion cells of the cat. Journal of Physiology, 187(3):517-552.
  7. Fix, J., Vitay, J., and Rougier, N. (2007). A distributed computational model of spatial memory anticipation during a visual search task. In Anticipatory Behavior in Adaptive Learning Systems, Lecture Notes in Artificial Intelligence, pages 170-188.
  8. Fouquier, G., Atif, J., and Bloch, I. (2008). Incorporating a pre-attention mechanism in fuzzy attribute graphs for sequential image segmentation. In Int. Conf. on Information Processing and Management of Uncertainty in Knowledge-Based Systems (IPMU), pages 840-847.
  9. Frintrop, S., Jensfelt, P., and Christensen, H. (2006). Attentional landmark selection for visual slam. In Int. Conf.
  10. on Intelligent Robots and Systems, pages 2582-2587.
  11. Gerstner, W. and Kistler, W. (2002). Spiking Neuron Models: Single Neurons, Population, Plasticity. Cambridge University Press, New York, NY, USA.
  12. Itti, L., Koch, C., and Niebur, E. (1998). A model of saliency-based visual attention for rapid scene analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 20(11):1254-1259.
  13. Itti, L., Rees, G., and Tsotsos, J., editors (2005). Neurobiology of Attention. Elsevier, San Diego, USA.
  14. König, P., Engel, A., and Singer, W. (1996). Integrator or coincidence detector? the role of the cortical neuron revisited. Trends in Neurosciences, 19(4):130-137.
  15. Maass, W. (1997). Networks of spiking neurons: the third generation of neural network models. Neural Networks, 10:1659-1671.
  16. Maillard, M., Gapenne, O., Gaussier, P., and Hafemeister, L. (2005). Perception as a dynamical sensori-motor attraction basin. In Advances in Artificial Life, volume 3630 of Lecture Notes in Computer Science, pages 37-46. Springer.
  17. Michalke, T., Fritsch, J., and Goerick, C. (2008). Enhancing robustness of a saliency-based attention system for driver assistance. In Int. Conf. on Computer Vision Systems (ICVS), volume 5008 of Lecture Notes in Computer Science, pages 43-55. Springer.
  18. Tsotsos, J. (1989). The complexity of perceptual search tasks. In Int. Joint Conf. on Artificial Intelligence (IJCAI), pages 1571-1577. AAAI, Detroit, USA.
  19. Tsotsos, J. (1990). Analysing vision at the complexity level. Behavioral and Brain Sciences, 13:423-469.
  20. Vitay, J., Rougier, N., and Alexandre, F. (2005). A distributed model of spatial visual attention. In Biomimetic Neural Learning for Intelligent Robots, Lecture Notes in Artificial Intelligence, pages 54-72. Springer.
  21. Wolff, C., Hartmann, G., and Ruckert, U. (1999). ParSPIKE-a parallel DSP-accelerator for dynamic simulation of large spiking neural networks. In Int. Conf. on Microelectronics for Neural, Fuzzy and BioInspired Systems (MicroNeuro), pages 324-331. IEEE Computer Society.
Download


Paper Citation


in Harvard Style

Chevallier S. and Dahdouh S. (2009). DIFFERENCE OF GAUSSIANS TYPE NEURAL IMAGE FILTERING WITH SPIKING NEURONS . In Proceedings of the International Joint Conference on Computational Intelligence - Volume 1: ICNC, (IJCCI 2009) ISBN 978-989-674-014-6, pages 467-472. DOI: 10.5220/0002322304670472


in Bibtex Style

@conference{icnc09,
author={Sylvain Chevallier and Sonia Dahdouh},
title={DIFFERENCE OF GAUSSIANS TYPE NEURAL IMAGE FILTERING WITH SPIKING NEURONS},
booktitle={Proceedings of the International Joint Conference on Computational Intelligence - Volume 1: ICNC, (IJCCI 2009)},
year={2009},
pages={467-472},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002322304670472},
isbn={978-989-674-014-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Joint Conference on Computational Intelligence - Volume 1: ICNC, (IJCCI 2009)
TI - DIFFERENCE OF GAUSSIANS TYPE NEURAL IMAGE FILTERING WITH SPIKING NEURONS
SN - 978-989-674-014-6
AU - Chevallier S.
AU - Dahdouh S.
PY - 2009
SP - 467
EP - 472
DO - 10.5220/0002322304670472