Skip to main content
SpringerLink
Log in

Component Fusion for Face Detection in the Presence of Heteroscedastic Noise

  • Conference paper
Pattern Recognition (DAGM 2003)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 2781))

Included in the following conference series:

Abstract

Face detection using components has been proved to produce superior results due to its robustness to occlusions and pose and illumination changes. A first level of processing is devoted to the detection of individual components, while a second level deals with the fusion of the component detectors. However, the fusion methods investigated up to now neglect the uncertainties that characterize the component locations. We show that this uncertainty carries important information that, when exploited, leads to increased face localization accuracy. We discuss and compare possible solutions taking into account geometrical constraints. The efficiency and usefulness of the techniques are tested with both synthetic and real world examples.

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. Cootes, T., Taylor, C.: Statistical models of appearance for computer vision. Technical report, University of Manchester (September 1999)

    Google Scholar 

  2. Cortes, C., Vapnik, V.: Support-vector networks. Machine Learning 20(3), 273–297 (1995)

    MATH  Google Scholar 

  3. Crow, F.: Summed-area tables for texture mapping. In: Proceedings of SIGGRAPH, vol. 18, pp. 207–212 (1984)

    Google Scholar 

  4. Freund, Y., Schapire, R.E.: Experiments with a new boosting algorithm. In: International Conference on Machine Learning, pp. 148–156 (1996)

    Google Scholar 

  5. Heisele, B., Serre, T., Pontil, M., Poggio, T.: Component-based face detection. In: CVPR 2001, pp. I-657–662 (2001)

    Google Scholar 

  6. Leung, T.K., Burl, M.C., Perona, P.: Finding faces in cluttered scenes using random labeled graph matching. In: Fifth Intl. Conf. on Comp. Vision (June 1995)

    Google Scholar 

  7. Matei, B.: Heteroscedastic errors-in-variables models in computer vision. Ph.D. Dissertation, Rutgers, the State University of New Jersey (May 2001)

    Google Scholar 

  8. Mohan, A., Papageorgiou, C., Poggio, T.: Example-based object detection in images by components. IEEE Trans. on PAMI 23(4) (2001)

    Google Scholar 

  9. Papageorgiou, C., Poggio, T.: A trainable system for object detection. IJCV 38(1), 15–33 (2000)

    Article  MATH  Google Scholar 

  10. Viola, P., Jones, M.: Robust real-time face detection. In: ICCV 2001, p. II: 747 (2001)

    Google Scholar 

  11. Yow, K., Cipolla, R.: Feature-based human face detection. IVC 15(9), 713–735 (1997)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Siemens Corporate Research, 755 College Road East, Princeton, NJ, 08540, USA

    Binglong Xie, Dorin Comaniciu & Visvanathan Ramesh

  2. Information and Communication Mobile, Siemens AG, Haidenauplatz 1, 81617, Muenchen, Germany

    Markus Simon

  3. Computer Science and Engineering Dept., Lehigh University, 19 Memorial Drive West, Bethlehem, PA, 18015, USA

    Terrance Boult

Authors
  1. Binglong Xie
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Dorin Comaniciu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Visvanathan Ramesh
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Markus Simon
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Terrance Boult
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Otto-von-Guericke University, 39106, Magdeburg, Germany

    Bernd Michaelis

  2. Institute for Electronics, Signal Processing and Communications (IESK), Otto-von-Guericke-University Magdeburg, P.O. Box 4120, D-39016, Magdeburg, Germany

    Gerald Krell

Rights and permissions

Reprints and permissions

Copyright information

© 2003 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Xie, B., Comaniciu, D., Ramesh, V., Simon, M., Boult, T. (2003). Component Fusion for Face Detection in the Presence of Heteroscedastic Noise. In: Michaelis, B., Krell, G. (eds) Pattern Recognition. DAGM 2003. Lecture Notes in Computer Science, vol 2781. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45243-0_56

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-45243-0_56

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-40861-1

  • Online ISBN: 978-3-540-45243-0

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation