Skip to main content

A New QPSO Based BP Neural Network for Face Detection

  • Conference paper
Fuzzy Information and Engineering

Part of the book series: Advances in Soft Computing ((AINSC,volume 40))

Abstract

Quantum-behaved Particle Swarm Optimization (QPSO) algorithm is a quantum-inspired version of the particle swarm optimization (PSO) algorithm, which outperforms traditional PSOs in search ability as well as having less parameter to control. In this paper, QPSO technique is introduced into BP neural network to instead adopting gradient descent method in BP learning algorithm. Due to the characteristic of the QPSO algorithm, the problems of traditional BPNN can be avoided, such as easily converging to local minimum. Then we adopt the new learning algorithm to training a neural network for face detection, and the experiment results testify its efficiency in this.

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

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 259.00
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 329.99
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. Van den Bergh, F.: An Analysis of Particle Swarm Optimizers. PhD Thesis. University of Pretoria (2001)

    Google Scholar 

  2. Rowley, H., Baluja, S., Kanade, T.: Neural network-based face detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 20, 23–38 (1998)

    Article  Google Scholar 

  3. Kennedy, J., Eberhart, R.C.: Particle Swarm Optimization. In: IEEE Int’l Conference on Neural Networks, pp. 1942–1948. IEEE Computer Society Press, Los Alamitos (1995)

    Google Scholar 

  4. Sun, J., Feng, B., Xu, W.: Particle swarm optimization with particles having quantum behavior. In: Congress on Evolutionary Computation, vol. 1, pp. 325–331 (2004)

    Google Scholar 

  5. Sun, J., Xu, W., Feng, B.: A Global Search Strategy of Quantum-behaved Particle Swarm Optimization. In: IEEE Conference on Cybernetics and Intelligent Systems, vol. 1, pp. 111–116. IEEE, Los Alamitos (2004)

    Chapter  Google Scholar 

  6. Sun, J., Xu, W., Feng, B.: Adaptive Parameter Control for Quantum-behaved Particle Swarm Optimization on Individual Level. In: IEEE International Conference on Systems, Man and Cybernetics, vol. 4, pp. 3049–3054. IEEE, Los Alamitos (2005)

    Chapter  Google Scholar 

  7. Huang, L., Shimizu, A., Kobatake, H.: Face Detection using a modified Radial Basis Function Neural Network. In: IEEE International Conference on Pattern Recognition, vol. 2, pp. 342–345. IEEE, Los Alamitos (2002)

    Google Scholar 

  8. Clerc, M., Kennedy, J.: The particle swarm: explosion, stability, and convergence in a multi-dimensional complex space. IEEE Transactions on Evolutionary Computation 6, 58–73 (2002)

    Article  Google Scholar 

  9. Shi, Y., Eberhart, R.C.: A Modified Particle Swarm optimizer. In: IEEE International Conference on Evolutionary Computation, pp. 69–73. IEEE Computer Society Press, Los Alamitos (1998)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Bing-Yuan Cao

Rights and permissions

Reprints and permissions

Copyright information

© 2007 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Li, S., Wang, R., Hu, W., Sun, J. (2007). A New QPSO Based BP Neural Network for Face Detection. In: Cao, BY. (eds) Fuzzy Information and Engineering. Advances in Soft Computing, vol 40. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-71441-5_40

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-71441-5_40

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-71440-8

  • Online ISBN: 978-3-540-71441-5

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics