Skip to main content

An improved multiplexed resistive network for analog image preprocessing

  • Part VIII: Implementations
  • Conference paper
  • First Online:
Artificial Neural Networks — ICANN'97 (ICANN 1997)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 1327))

Included in the following conference series:

Abstract

We present an improved multiplexed analog resistive network for image preprocessing that features both edge detection and image segmentation without using resistive fuses. Based on a two-layer resistive network which performs Difference-of-two-Gaussians (DoG) spatial bandpass filtering, one layer of the network is multiplexed to implement both DoG and image segmentation by using the extracted edge information to control its resistors. The horizontal resistors are realized with single MOS transistors operating in the triode region. Their gates are supplied with high voltages generated on-chip by charge pumping devices to ensure operation in linear region. Additionally, a new algorithm for zero-crossing determination to detect edges is implemented, resulting in a significant reduction of about 40% in the number of transistors compared to existing methods.

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.

References

  1. C. Mead, M. Ismail: Analog VLSI Implementation of Neural Systems, Kluwer Academic Publishers, 1989

    Google Scholar 

  2. W. Bair and C. Koch: Real-time motion detection using an analog VLSI zero-crossing chip, SPIE Vol. 1473 Visual Information Processing, 1991

    Google Scholar 

  3. T. Poggio and C. Koch: Ill-Posed Problems in Early Vision, From Computational Theory, Nature, Vol. 317, 1985, pp. 314–319

    Google Scholar 

  4. P. Yu et al.: CMOS Resistive Fuses for Image Smoothing and Segmentation, IEEE Journal of Solid-State Circuits, vol. 27, no. 4, April 1992, pp. 545–553

    Google Scholar 

  5. C. Yi, R. Schlabbach, H. Kroth, H. Klar: A new bio-inspired algorithm for early vision edge detection and image segmentation, to be published in the Proceedings of IWANN '97 (International Work-conference on Artificial Neural Networks)

    Google Scholar 

  6. M. Schanz et al.: A CMOS Linear Image Sensor Array with On-Chip Programmable Signal Processing, ESSCIRC '95, Lille-France, Sept. 1995

    Google Scholar 

  7. John F. Dickson: On chip high voltage generation in NMOS integrated circuits using an improved voltage multiplier technique, IEEE J. of Solid State Circuits, June 1976, pp. 374–378

    Google Scholar 

  8. J. Babanezhad and G. Temes: A 20-V Four-Quadrant CMOS Analog Multiplier, IEEE Journal of Solid-State Circuits, vol. SC-20, no. 6, Dec. 1985

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Wulfram Gerstner Alain Germond Martin Hasler Jean-Daniel Nicoud

Rights and permissions

Reprints and permissions

Copyright information

© 1997 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Yi, CH., Schlabbach, R., Kroth, H., Klar, H. (1997). An improved multiplexed resistive network for analog image preprocessing. In: Gerstner, W., Germond, A., Hasler, M., Nicoud, JD. (eds) Artificial Neural Networks — ICANN'97. ICANN 1997. Lecture Notes in Computer Science, vol 1327. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0020309

Download citation

  • DOI: https://doi.org/10.1007/BFb0020309

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-63631-1

  • Online ISBN: 978-3-540-69620-9

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics