Skip to main content
SpringerLink
Log in

Ganglion-Based Balance Design of Multi-Layer Model and Its Watchfulness-Keeping

  • Regular Paper
  • Published:
Journal of Computer Science and Technology Aims and scope Submit manuscript

Abstract

An important problem of machine vision is the balance among the efficiency, accuracy and computation cost. The visual system of man can keep watchfulness to the perimeter of a visual field and subtly process information emerging in the center of the visual field at the same time. This kind of requirement assignment of computation can virtually ease the demand of hardware both in quantity and complexity. Therefore designing an artificial model based on biological mechanism is an effective approach. In this paper a multi-layer neural model is designed based on the multi-scale receptive fields of ganglions in retina. The model can keep watch on the periphery part of a scene while processing the center information of the scene. And why it can balance the hardware complexity, processing precision and computational intensity is analyzed. An experiment is done to test the model's sensitivity in watchfulness keeping and its efficiency and veracity in environment sampling. This model may provide valuable inspiration in the implementation of real-time processing and the avoidance of expensive computation cost in machine vision.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

References

  1. Erten G, Salam F. Real-time realization of early visual perception. Int. Journal of Computers and Electrical Engineering, Special Issue on Micro-Electronic Hardware Implementation of Soft Computing: Neural and Fuzzy Networks with Learning, 1999, 4(2/3), 379–407.

    Google Scholar 

  2. Conklin C, Watkins R, Foo S et al. Dichromatic color perception: A fast alternative for machine vision systems. Engineering Applications of Artificial Intelligence, 2002, 15(5): 351–355.

    Google Scholar 

  3. David K Andes, James C Witham, Michael D Miles. MAVIS: A special purpose neural computational system for ATR. Neural Networks, 1995, 8(7/8): 1349–1358.

    Google Scholar 

  4. Ito Y, Yagi T, Kanda H et al. Cultures of neurons on micro-electrode array in hybrid retinal implant. In Proc. 1999 IEEE Int. Conf. Systems, Man and Cybernetics, IV, Tokyo, Japan, 1999, pp.414–417.

  5. Resatz S, Rattay F. Excitability of bipolar and ganglion cells with retinal prosthesis: A modeling study. Engineering in Medicine and Biology Society 2003. In Proc. the 25th Annual Int. Conf. the IEEE, Cancum, Mexico, Sept. 17–21, 2003, Vol.3, pp.2039–2042.

  6. Prhahg F, Piittjer D, BuB R et al. Intraocular vision aid (IOS): Optical signal transmission and image generation. In Proc. the 22nd Annual Int. Conf. the IEEE, Engineering in Medicine and Biology Society, Chicago, USA, July 23–28, 2000, Vol.1, pp.796–797.

  7. Ela Claridge, Ian R Billups. Towards a method for parameterizing models of early vision using psychophysical data. Image and Vision Computing, 1998, 16(6/7): 473–498.

    Google Scholar 

  8. Nader M Nofal, Hazem H Ali, M E Zaghloul. A CMOS visual system using CRM. In IEEE Proc. 1998 Midwest Symposium on Systems and Circuits, South Bend, Indiana, August 9–12, 1998, pp.552–555.

  9. Markus Schwarz, Ralf Hauschild, Bedrich J Hosticka et al. Single-chip CMOS image sensors for a retina implant system. IEEE Trans. Circuits and Systemsp–II: Analog and Digital Signal Processing, 1999, 46(7): 870–877.

    Google Scholar 

  10. Chiang C-T, Wu C-Y. Implantable neuromorphic vision chips. Electronic Letters, 2004, 40(6): 478–479.

    Article  Google Scholar 

  11. Kareem A Zaghloul, Kwabena Boahen. Optic nerve signals in a neuromorphic chip II: Testing and results. IEEE Trans. Biomedical Engineering, 2004, 51(4): 667–675.

    Google Scholar 

  12. Thomas Stieglitz, Hansjoerg Beutel, Ralf Keller et al. Integrative design and hybrid assembly of a flexible retina implant system. In Proc. the First Joint BMES & EMBS Conference Serving Humanity, Advancing Technology, Atlanta, GA, USA, Oct. 13–16, 1999, p.474.

  13. Rolf Eckmiller, Michael Becker, Ralph Hunermann. Towards a learning retina implant with epiretinal contacts. In Proc. the IEEE Int. Conf. Systems, Man and Cybernetics, Tokyo, Japan, 1999, Vol.4, pp.12–15.

  14. Ales Leonardis, Horst Bischof. Kernel and subspace methods for computer vision. Pattern Recognition, 2003, 36(9): 1925–1927.

    Google Scholar 

  15. Murino V, Vernazza G. Artificial neural networks for image analysis and computer vision. Image and Vision Computing, 2001, 19: 583–584.

    Article  Google Scholar 

  16. Fleet D J. The early processing of spatio-temporal visual information [Thesis]. University of Toronto, Sept. 1984.

  17. William R Hendee, Peter N T Wells. The Perception of Visual Information. Springer-Verlag, New York, Inc., 1997.

    Google Scholar 

  18. Wills D S, Baker J M, Cat H H et al. Processing architectures for smart pixel systems. IEEE Journal of Selected Topics in Quantum Electronics, 1996, 2(1): 24–34.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Lab of Algorithm for Cognitive Model of Department of Computer Science, Brain Science Research Center Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, 200433, P.R. China

    Hui Wei

  2. Intelligence Engineering Lab, Institute of Software, Chinese Academy of Sciences, Beijing, 100080, P.R. China

    Shang-Min Luan

Authors
  1. Hui Wei
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Shang-Min Luan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hui Wei.

Additional information

This research is supported by the NSFC under Grant No.60303007, the National Basic Research 973 Program of China under Grant No.2001CB309401, and the open project of Key Laboratory of Intelligent Information Processing, ICT of CAS under Grant No.IIP2002-3.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Wei, H., Luan, SM. Ganglion-Based Balance Design of Multi-Layer Model and Its Watchfulness-Keeping. J Comput Sci Technol 20, 567–573 (2005). https://doi.org/10.1007/s11390-005-0567-2

Download citation

  • Received:

  • Revised:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11390-005-0567-2

Keywords

Search

Navigation