Skip to main content
SpringerLink
Log in

Human Face Detection Using New High Speed Modular Neural Networks

  • Conference paper
Artificial Neural Networks: Biological Inspirations – ICANN 2005 (ICANN 2005)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 3696))

Included in the following conference series:

  • 1583 Accesses

Abstract

In this paper, a new approach to reduce the computation time taken by neural networks for the searching process is introduced. Both fast and cooperative modular neural networks are combined to enhance the performance of the detection process. Such approach is applied to identify human faces automatically in cluttered scenes. In the detection phase, neural networks are used to test whether a window of 20 × 20 pixels contains a face or not. The major difficulty in the learning process comes from the large database required for face / nonface images. A simple design for cooperative modular neural networks is presented to solve this problem by dividing these data into three groups. Such division results in reduction of computational complexity and thus decreasing the time and memory needed during the test of an image. Simulation results for the proposed algorithm on Bio database show a good performance.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
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. Rowley, H.A., Baluja, S., Kanade, T.: Neural Network - Based Face Detection. IEEE Trans. on Pattern Analysis and Machine Intelligence 20(1), 23–38 (1998)

    Article  Google Scholar 

  2. Jacobs, R., Jordan, M., Barto, A.: Task Decomposition Through Competition in a Modular Connectionist Architecture: The what and where vision tasks. Neural Computation 3, 79–87 (1991)

    Article  Google Scholar 

  3. El-Bakry, H.M.: Automatic Human Face Recognition Using Modular Neural Networks. Machine Graphics & Vision Journal (MG&V) 10(1), 47–73 (2001)

    Google Scholar 

  4. Klette, R., Zamperon, P.: Handbook of image processing operators. John Wiley & Sons ltd, Chichester (1996)

    Google Scholar 

  5. El-Bakry, H.M.: Human Iris Detection Using Fast Cooperative Modular Neural Networks and Image Decomposition. Machine Graphics & Vision Journal (MG&V) 11(4), 498–512 (2002)

    Google Scholar 

  6. Alpaydin, E.: Multiple Networks for Function Learning. In: Int. Conf. on Neural Networks, vol. 1, pp. 9–14 (1993)

    Google Scholar 

  7. Waibel, A.: Modular Construction of Time Delay Neural Networks for Speech Recognition. Neural Computing 1, 39–46 (1989)

    Article  Google Scholar 

  8. Joe, K., Mori, Y., Miyake, S.: Construction of a large scale neural network: Simulation of handwritten Japanese Character Recognition. NCUBE Concurrency 2(2), 79–107 (1990)

    Google Scholar 

  9. El-bakry, H.M.: Automatic Personal Identification Using Neural Networks. In: The 24th international Conf. On Statistics computer Science, and its applications, Egypt, Cairo, pp. 405–416 (1999)

    Google Scholar 

  10. Ben-Yacoub, S.: Fast Object Detection using MLP and FFT, IDIAP-RR 11, IDIAP (1997)

    Google Scholar 

  11. El-Bakry, H.M.: Fast Face Detection Using Neural Networks and Image Decomposition. In: Proc. of the 6th International Computer Science Conference, Active Media Technology, Hong Kong – China, December 18-20, pp. 205–215 (2001)

    Google Scholar 

  12. El-Bakry, H.M.: Face Detection Using Fast Neural Networks and Image Decomposition. In: Proc. of INNS-IEEE International Joint Conference on Neural Networks, Honolulu, Hawaii, USA, 14-19 May (2002)

    Google Scholar 

  13. El-Bakry, H.M.: Comments on Using MLP and FFT for Fast Object/Face Detection. In: Proc. of IEEE IJCNN 2003, Portland, Oregon, July 20-24, pp. 1284–1288 (2003)

    Google Scholar 

  14. El-Bakry, H.M., Stoyan, H.: Fast Neural Networks for Sub-Matrix (Object/Face) Detection. In: Proc. of IEEE International Symposium on Circuits and Systems, Vancouver, Canada, 23-26 May (2004)

    Google Scholar 

  15. El-Bakry, H.M.: Fast Sub-Image Detection Using Neural Networks and Cross Correlation in Frequency Domain. In: Proc. of IS 2004: 14th Annual Canadian Conference on Intelligent Systems, Ottawa, Ontario, 6-8 June (2004)

    Google Scholar 

  16. El-Bakry, H.M., Stoyan, H.: Fast Neural Networks for Code Detection in a Stream of Sequential Data. In: Proc. of CIC 2004 International Conference on Communications in Computing, Las Vegas, Nevada, USA, 21-24 June (2004)

    Google Scholar 

  17. El-Bakry, H.M.: Fast Neural Networks for Object/Face Detection. In: Proc. of 5th International Symposium on Soft Computing for Industry with Applications of Financial Engineering, Sevilla, Andalucia, Spain, June 28-July 4 (2004)

    Google Scholar 

  18. El-Bakry, H.M., Stoyan, H.: A Fast Searching Algorithm for Sub-Image (Object/Face) Detection Using Neural Networks. In: Proc. of the 8th World Multi-Conference on Systemics, Cybernetics and Informatics, Orlando, USA, 18-21 July (2004)

    Google Scholar 

  19. El-Bakry, H.M., Stoyan, H.: Fast Neural Networks for Code Detection in Sequential Data Using Neural Networks for Communication Applications. In: Proc. of the First International Conference on Cybernetics and Information Technologies, Systems and Applications: CITSA 2004, Orlando, Florida, USA, 21-25 July, vol. IV, pp. 150–153 (2004)

    Google Scholar 

  20. El-Bakry, H.M., Zhao, Q.: Fast Object/Face Detection Using Neural Networks and Fast Fourier Transform. International Journal of Signal Processing 1(3), 182–187 (2004)

    Google Scholar 

  21. El-Bakry, H.M., Zhao, Q.: A Fast Neural Algorithm for Serial Code Detection in a Stream of Sequential Data. International Journal of Information Technology 2(1), 71–90 (2005)

    Google Scholar 

  22. El-Bakry, H.M., Zhao, Q.: Fast Pattern Detection Using Neural Networks Realized in Frequency Domain. In: Proc. of the International Conference on Pattern Recognition and Computer Vision, The Second World Enformatika Congress WEC 2005, Istanbul, Turkey, 25-27 February, pp. 89–92 (2005)

    Google Scholar 

  23. El-Bakry, H.M., Zhao, Q.: Fast Pattern Detection Using Normalized Neural Networks and Cross Correlation in the Frequency Domain. Accepted and under publication in the EURASIP Journal on Applied Signal Processing

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. University of Aizu, Aizu Wakamatsu, 965-8580, Japan

    Hazem M. El-Bakry

Authors
  1. Hazem M. El-Bakry
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Department of Informatics, Nicolaus Copernicus University, Toruń, Poland

    Włodzisław Duch

  2. Systems Research Institute, Polish Academy of Sciences, ul. Newelska 6, 01–447, Warsaw, Poland

    Janusz Kacprzyk

  3. Adaptive Informatics Research Centre, Helsinki University of Technology, P.O. Box 5400, 02015 HUT, Finland

    Erkki Oja

  4. Systems Research Institute, Polish Academy of Sciences, ul. Newelska 6, 01-447, Warsaw, Poland

    Sławomir Zadrożny

Rights and permissions

Reprints and permissions

Copyright information

© 2005 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

El-Bakry, H.M. (2005). Human Face Detection Using New High Speed Modular Neural Networks. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds) Artificial Neural Networks: Biological Inspirations – ICANN 2005. ICANN 2005. Lecture Notes in Computer Science, vol 3696. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11550822_85

Download citation

  • DOI: https://doi.org/10.1007/11550822_85

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-28752-0

  • Online ISBN: 978-3-540-28754-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation