Skip to main content

A Neural Network Feature Detector Using a Multi-Resolution Pyramid

  • Chapter
Neural Networks for Vision, Speech and Natural Language

Part of the book series: BT Telecommunications Series ((BTTS,volume 1))

Abstract

This chapter describes a technique used to solve the problem of accurately locating the positions of eyes within a particular set of sixty images supplied by BT; half of the images could be used as training data, the other half as test data. The subjects in each image are at the same viewing distance, the faces are roughly in a vertical position, with a face in the centre of the frame looking forward with eyes open and directed at the camera.

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

Access this chapter

eBook
USD 16.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Ellacott S. W., Evans M. & Hand C. C.: ‘Training Neural Networks Using a MultiResolution Pyramid — an interim Report’, Research Report for British Telecom’s Connectionist Project (1989).

    Google Scholar 

  2. Schalkoff R. J.: ‘Digital Image Processing and Computer Vision’, John Wiley & Sons, inc (1989).

    Google Scholar 

  3. Levine M. D.: ‘Region Analysis Using a Pyramid Data Structure’. in Tanimoto S. & Klinger A. (Eds), Structured Computer Vision, New York, Academic Press (1980).

    Google Scholar 

  4. Tanimoto S.: ‘Image Data Structures’. in Tanimoto S. & Klinger A. (Eds) Structured Computer Vision, New York, Academic Press (1980).

    Google Scholar 

  5. Rumelhart D. E., Hinton G. E. & Williams R. J.: ‘Learning Representations by Back-Propagating Errors’, Nature, 323, pp 533–536 (1986a).

    Article  Google Scholar 

  6. Rumelhart D. E., Hinton G. E. & Williams R. J.: ‘Learning internal Representations by Error Propagation’. in Rumelhart D. E. & McClelland, J. L., ‘Parallel Distributed Processing: Explorations in the microstructure of cognition’, 1, Cambridge Mass, MIT Press (1986b).

    Google Scholar 

  7. Sejnowski T. J. & Rosenberg C. R.: ‘NETtalk: A Parallel Network that Learns to Read Aloud’. in anderson A. & Rosenfeld E., ‘neurocomputing: foundations of research’, Cambridge Mass, MIT Press (1986).

    Google Scholar 

  8. Plaut D. C. & Hinton G. E.: ‘Learning Sets of Filters Using Back-Propagation’, Computer Speech and Language, 2, pp 35–61 (1987).

    Article  Google Scholar 

  9. Gorman R. P. & Sejnowski T. J.: ‘Analysis of Hidden Units in a Layered Network Trained to Classify Sonar Targets’, neural Networks, 1, pp 75–89 (1988).

    Article  Google Scholar 

  10. Tesauro G. & Sejnowski T. J.: ‘A Parallel Network that Learns to Play Backgammon’, Artificial intelligence, 39, pp 357–390 (1989).

    Article  MATH  Google Scholar 

  11. McClelland J. L. & Rumelhart D. E.: ‘Explorations in Parallel Distributed Processing: A Handbook of Models, Programs, and Exercises’, Cambridge Mass, MIT Press (1988).

    Google Scholar 

  12. Barrow H.: ‘neural Networks Tutorial’ AISB 89 Conference, Sussex University (18th April 1989).

    Google Scholar 

  13. Ellacott S. W.: ‘An Analysis of the Delta Rule’, inNC-90, int Neural Network Conf, 2, Paris, pp 956–959 (July 9-13 1990).

    Google Scholar 

  14. Hutchinson R. A. & Welsh W. J.: ‘Comparison of Neural Networks and Conventional Techniques for Feature Location in Facial Images’, Proc First IEE int Conf on Artificial Neural Networks, London (1989).

    Google Scholar 

  15. Lang K. J. & Witbrock M. J.: ‘Learning to Tell Two Spirals Apart’, in Proceedings of the 1988 Connectionist Models Summer School, Morgan Kaufman, California (1989).

    Google Scholar 

  16. Isaacson E. & Keller H. B.: ‘Analysis of Numerical Methods’, (chapter 1), John Wiley & Sons, New York (1966).

    MATH  Google Scholar 

  17. Barrodale I. & Roberts F. D. K.: ‘An Improved Algorithm for Discrete 11 Linear Approximation’, SIAM J Numerical Analysis, 10, pp 839–848 (1973).

    Article  MathSciNet  MATH  Google Scholar 

  18. Gill P. E., Murray W. & Wright M. H.: ‘Practical Optimization’, New York, Academic Press (1981).

    MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 1992 British Telecommunications plc

About this chapter

Cite this chapter

Hand, C.C., Evans, M.R., Ellacott, S.W. (1992). A Neural Network Feature Detector Using a Multi-Resolution Pyramid. In: Linggard, R., Myers, D.J., Nightingale, C. (eds) Neural Networks for Vision, Speech and Natural Language. BT Telecommunications Series, vol 1. Springer, Dordrecht. https://doi.org/10.1007/978-94-011-2360-0_6

Download citation

  • DOI: https://doi.org/10.1007/978-94-011-2360-0_6

  • Publisher Name: Springer, Dordrecht

  • Print ISBN: 978-94-010-5041-8

  • Online ISBN: 978-94-011-2360-0

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics