Face Finding in Images

  • John M. Vincent


This chapter describes work undertaken at BT Laboratories to produce a system, based on the use of neural network feature detectors, to robustly locate and track features in digital image sequences. We have concentrated on the location of eyes and mouths in human head-and-shoulders images, although the techniques described should be applicable to determining the position of localised features in other objects.


Feature Point Search Region Pattern Vector Pixel Expansion Single Training Session 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Nightingale C, Hutchinson R A, “Artificial neural nets and their application to image processing”, British Telecom Technology Journal, Vol. 8, No. 3, pp. 81–93, July 1990.Google Scholar
  2. [2]
    Hines E, and Hutchinson R A, “Application of Multi-layer Perceptrons to Facial Feature Location”, Proc. 3rd IEE Int. Conf. on Image Processing and its Applications, Warwick UK, July 1989.Google Scholar
  3. [3]
    Hutchinson R A and Welsh W J, “Comparison of Neural Networks and Conventional Techniques for Feature Location in Facial Images”, Proc. 1st IEE Int. Conf. on Artificial Neural Networks, London, October 1989.Google Scholar
  4. [4]
    Vincent J M, “Facial Feature Location in Coarse Resolution Images by Multi-Layered Perceptions”, Proc. Int. Conf. on Artificial Neural Networks (ICANN-91), Vol. I, pp. 821-826, 24–28 June 1991, Elsevier Science.Google Scholar
  5. [5]
    Vincent J M, Myers D J, Hutchinson R A, “Image feature location in multi-resolution images using a hierarchy of multi-layered perceptions”, in, Lingard, Myers and Nightingale (Eds): ‘Neural networks for images, speech and natural language’, Chapman Hall, UK, 1992.Google Scholar
  6. [6]
    Vincent J M, Waite J B, Myers D J, “Location of feature points in images using neural networks”, BT Technology Journal, Vol 10, No 3, July 1992.Google Scholar
  7. [7]
    Waite J B, “Facial Feature Location Using Multilayer Perceptrons and Micro-features”, Proc. IEEE Int. Jnt. Conf. on Neural Networks (IJCNN-91), Vol. 1, pp. 292–299, 18–21 Nov. 1991.Google Scholar
  8. [8]
    Vincent J M, Waite J B, Myers D J, “Precise location of facial features by a hierarchical assembly of neural nets”, Proc. IEE 2nd Int. Conf. on Artificial Neural Networks, ANN-91, 18–20 November 1991, pp. 69-73.Google Scholar
  9. [9]
    Vincent J M, Waite J B, Myers D J, “Automatic location of visual features by a system of multilayered perceptrons”, IEE Proceedings-F, Vol. 139, No. 6, pp. 405-12, December 92.Google Scholar
  10. [10]
    Maxwell T et Al, “Transformation Invariance Using High Order Correlations in Neural Net Architectures” IEEE Int. Conf. on Systems Man and Cybernetics, Atlanta, Georgia. October 1986.Google Scholar
  11. [11]
    Rumelhardt D E, and McClelland J L, Parallel Distributed Processing; Volume 1: Foundations”, The MIT Press 1987.Google Scholar
  12. [12]
    Allred L G, Kelly G E, “Supervised learning techniques for backpropagation networks”, Proc. IJCNN, 1990, Vol. 1, pp. 721-8.Google Scholar
  13. [13]
    Popesco V, Vincent J M, “Location of facial features using a Bolzmann machine to implement geometrical constraints”, Chapter 14 in ‘Techniques and applications of neural networks’, Taylor M, Lisboa P (Eds), Ellis Horwood Workshop Series, 1993, Ellis Horwood.Google Scholar
  14. [14]
    Wan E A, “Neural Network Classification: A Bayesian Interpretation”, IEEE Trans. Neural Networks, Vol. 1, No. 4, pp. 303–305, Dec. 1990.CrossRefGoogle Scholar
  15. [15]
    Ruck D W, et al, “The Multilayer Perception as an Approximation to a Bayes Optimum Discriminant function”, IEEE Trans. Neural Networks, Vol. 1, No. 4, pp. 296–298, Dec. 1990.CrossRefGoogle Scholar
  16. [16]
    Orrey D A, Myers D J, Vincent J M, “A High Performance Digital Processor for Implementing Large Artificial Neural Networks”, Proc. Custom Integrated Circuit Conference CICC-91, San Diego, Ca., 12–15 May 1991.Google Scholar

Copyright information

© Springer Science+Business Media New York 1995

Authors and Affiliations

  • John M. Vincent
    • 1
  1. 1.BT LaboratoriesMartlesham HeathIpswichUK

Personalised recommendations