Skip to main content
SpringerLink
Log in

The Fast and the Flexible: Extended Pseudo Two-Dimensional Warping for Face Recognition

  • Conference paper
Pattern Recognition and Image Analysis (IbPRIA 2011)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 6669))

Included in the following conference series:

Abstract

In this work, we propose a novel extension of pseudo 2D image warping (P2DW) which allows for joint alignment and recognition of non-rectified face images. P2DW allows for optimal displacement inference in a simplified setting, but cannot cope with stronger deformations since it is restricted to column-to-column mapping. We propose to implement additional flexibility in P2DW by allowing deviations from column centers while preserving vertical structural dependencies between neighboring pixel coordinates. In order to speed up the recognition we employ hard spacial constraints on candidate alignment positions. Experiments on two well-known face datasets show that our algorithm significantly improves the recognition quality under difficult variability such as 3D rotation (poses), expressions and illuminations, and can reliably classify even automatically detected faces. We also show an improvement over state-of-the-art results while keeping computational complexity low.

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. Arashloo, S., Kittler, J.: Hierarchical image matching for pose-invariant face recognition. In: BMVC (2009)

    Google Scholar 

  2. Dreuw, P., Steingrube, P., Hanselmann, H., Ney, H.: Surf-face: Face recognition under viewpoint consistency constraints. In: BMVC (2009)

    Google Scholar 

  3. Ekenel, H.K., Stiefelhagen, R.: Analysis of local appearance-based face recognition: Effects of feature selection and feature normalization. In: CVPRW, Washington, DC, USA, p. 34 (2006)

    Google Scholar 

  4. Eickeler, S., Mller, S., Rigoll, G.: High performance face recognition using pseudo 2-d hidden markov models. In: ECCV (1999)

    Google Scholar 

  5. Gass, T., Dreuw, P., Ney, H.: Constrained energy minimisation for matching-based image recognition. In: ICPR, Istanbul, Turkey (2010) (in press)

    Google Scholar 

  6. Gross, R.: http://ralphgross.com/FaceLabels

  7. Keysers, D., Unger, W.: Elastic image matching is np-complete. Pattern Recognition Letters 24, 445–453 (2003)

    Article  MATH  Google Scholar 

  8. Ke, Y., Sukthankar, R.: Pca-sift: A more distinctive representation for local image descriptors. In: CVPR, vol. (2), pp. 506–513 (2004)

    Google Scholar 

  9. Kolmogorov, V.: Convergent tree-reweighted message passing for energy minimization. IEEE TPAMI 28, 1568–1583 (2006)

    Article  Google Scholar 

  10. Kuo, S.S., Agazzi, O.E.: Keyword spotting in poorly printed documents using pseudo 2-d hidden markov models. IEEE TPAMI 16(8), 842–848 (1994)

    Article  Google Scholar 

  11. Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60(2), 91–110 (2004)

    Article  Google Scholar 

  12. Martinez, A., Benavente, R.: The AR face database. Technical report, CVC Technical report (1998)

    Google Scholar 

  13. Mottl, V., Kopylov, A., Kostin, A., Yermakov, A., Kittler, J.: Elastic transformation of the image pixel grid for similarity based face identification. In: ICPR (2002)

    Google Scholar 

  14. Samaria, F.: Face Recognition Using Hidden Markov Models. PhD thesis, Cambridge University (1994)

    Google Scholar 

  15. Sarfraz, M.S., Hellwich, O.: Probabilistic learning for fully automatic face recognition across pose. Image and Vision Computing 28(5), 744–753 (2010)

    Article  Google Scholar 

  16. Smith, S.J., Bourgoin, M.O., Sims, K., Voorhees, H.L.: Handwritten character classification using nearest neighbor in large databases. IEEE TPAMI 16(9), 915–919 (1994)

    Article  Google Scholar 

  17. Sim, T., Baker, S., Bsat, M.: The CMU pose, illumination, and expression (PIE) database. In: AFGR (2002)

    Google Scholar 

  18. Tan, K., Chen, S.: Adaptively weighted sub-pattern pca for face recognition. Neurocomputing 64, 505–511 (2005)

    Article  Google Scholar 

  19. Uchida, S., Sakoe, H.: A monotonic and continuous two-dimensional warping based on dynamic programming. In: ICPR, pp. 521–524 (1998)

    Google Scholar 

  20. Viola, P., Jones, M.: Robust real-time face detection. International Journal of Computer Vision 57(2), 137–154 (2004)

    Article  Google Scholar 

  21. Wiskott, L., Fellous, J.M., Krg̈er, N., von der Malsburg, C.: Face recognition by elastic bunch graph matching. IEEE TPAMI 19, 775–779 (1997)

    Article  Google Scholar 

  22. Wright, J., Hua, G.: Implicit elastic matching with random projections for pose-variant face recognition. In: CVPR, pp. 1502–1509 (2009)

    Google Scholar 

  23. Zhang, X., Gao, Y., Leung, M.K.H.: Recognizing rotated faces from frontal and side views: An approach toward effective use of mugshot databases. IEEE TIFS 3(4), 684–697 (2008)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Computer Vision and Multimodal Computing, MPI Informatics, Saarbruecken, Germany

    Leonid Pishchulin

  2. Computer Vision Laboratory, ETH Zurich, Switzerland

    Tobias Gass

  3. Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Germany

    Leonid Pishchulin, Tobias Gass, Philippe Dreuw & Hermann Ney

Authors
  1. Leonid Pishchulin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Tobias Gass
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Philippe Dreuw
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Hermann Ney
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Departament de Matemàtica Aplicada i Anàlisi, Universitat de Barcelona, Facultat de Matemàtiques, Gran Via de les Corts Catalanes 585, 08007, Barcelona, Spain

    Jordi Vitrià

  2. Instituto de Sistemas e Robótica / Instituto Superior Técnico, Av. Rovisco Pais, 1, 1049-001, Lisbon, Portugal

    João Miguel Sanches

  3. Institute for Intelligent Systems and Numerical Applications in Engineering (SIANI), Edificio de Informática y Matemáticas, University of Las Palmas de Gran Canaria, Campus Universitario de Tafira, 35017, Las Palmas, Spain

    Mario Hernández

Rights and permissions

Reprints and permissions

Copyright information

© 2011 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Pishchulin, L., Gass, T., Dreuw, P., Ney, H. (2011). The Fast and the Flexible: Extended Pseudo Two-Dimensional Warping for Face Recognition. In: Vitrià, J., Sanches, J.M., Hernández, M. (eds) Pattern Recognition and Image Analysis. IbPRIA 2011. Lecture Notes in Computer Science, vol 6669. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21257-4_7

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-21257-4_7

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-21256-7

  • Online ISBN: 978-3-642-21257-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation