Skip to main content
SpringerLink
Log in

Quasi-invariant Illumination Recognition for Appearance-Based Models, Taking Advantage of Manifold Information and Non-uniform Sampling

  • Conference paper
MICAI 2009: Advances in Artificial Intelligence (MICAI 2009)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 5845))

Included in the following conference series:

  • 1523 Accesses

Abstract

The appearance of an object can be greatly affected by the changes in illumination conditions in the scene where that object is seen. In this paper, we propose a novel method for building appearance-based models that are tolerant to lighting variations. This new approach is based on a Non-Uniform Sampling technique, so that we use a very small number of images for generating those models, and this reduces the computing time and storage space required for the modeling stage, with respect to Uniform Sampling techniques. We have tested the proposed algorithm with a comprehensive set of objects with different appearance, and the high recognition rate obtained in these experiments shows the effectiveness of the proposed method. Also, the necessary time to compute the associated manifold in eigenspace is dramatically reduced.

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. Nayar, S.K., Murase, H., Nene, S.A.: Parametric Appearance Representation. In: Nayar, S.K., Poggio, T. (eds.) Early Visual Learning, pp. 131–160. Oxford University Press, Oxford (1996)

    Google Scholar 

  2. Belhumeur, P.N., Kriegman, D.J.: What is the Set of Images of an Object under All Possible Illumination Conditions? International Journal of Computer Vision 28(3), 245–260 (1998)

    Article  Google Scholar 

  3. Forsyth, D., Ponce, J.: Computer Vision: a Modern Approach. Prentice Hall, Englewood Cliffs (2003)

    Google Scholar 

  4. Georghiades, A., Kriegman, D.J., Belhumeur, P.N.: Illumination Cones for Recognition under Variable Illumination: Faces. In: CVPR 1998, pp. 52–58. IEEE Computer Society Press, Los Alamitos (1998)

    Google Scholar 

  5. Chin, T.J., Suter, D.: A Study of Illumination Cones Method for Face Recognition Under Variable Illumination. Technical Report. MECSE-7-2004. Department of Electrical and Comp. Systems Engineering, Monash University (2004)

    Google Scholar 

  6. Jacobs, D.W., Belhumeur, P.N., Basri, R.: Comparing Images under Variable Illumination. In: CVPR 1998, pp. 610–617. IEEE Computer Society Press, Los Alamitos (1998)

    Google Scholar 

  7. Koenderink, J.J., van Doorn, A.J.: Photometric Invariants related to solid Shape. Optica Acta 27(7), 981–996 (1980)

    MathSciNet  Google Scholar 

  8. Lamdan, Y., Schwartz, J.T., Wolfson, H.J.: Affine Invariant Model-Based Object Recognition. IEEE Trans. on Robotics and Automation 6, 578–589 (1990)

    Article  Google Scholar 

  9. Wolff, L., Fan, J.: Segmentation of Surface Curvature with a Photometric Invariant. J. Opt. Soc. Am. A 11(11), 3090–3100 (1994)

    Article  Google Scholar 

  10. Schmid, C., Mohr, R.: Local grayvalue invariants for image retrieval. IEEE Trans. on Pattern Analysis and Machine Intelligence 19(5), 530–535 (1997)

    Article  Google Scholar 

  11. Chen, H.F., Belhumeur, P.N., Jacobs, D.W.: In Search of Illumination Invariants. In: CVPR 2000, pp. 254–261. IEEE Computer Society Press, Los Alamitos (2000)

    Google Scholar 

  12. Bischof, H., Wildenauer, H., Leonardis, A.: Illumination Insensitive Recognition Using Eigenspaces. Comp. Vision and Image Underst. 95, 86–104 (2004)

    Article  Google Scholar 

  13. Epstein, R., Hallinan, P.W., Yuille, A.L.: 5 ± 2 Eigenimages Suffice: an Empirical Investigation of Low-Dimensional Lighting Models. Workshop on Physics-Base Modeling in Computer Vision (1995)

    Google Scholar 

  14. Murase, H., Nayar, S.K.: Visual Learning of Object Models from Appearance. Technical Report. CUCS-054-92. Columbia University (1992)

    Google Scholar 

  15. Altamirano, L.C., Altamirano, L., Alvarado, M.: Non-uniform sampling for improve appearance-based models. Pattern Recognition Letters 23(1-3), 521–535 (2003)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Benemérita Universidad Autónoma de Publa-FCC, Boulevard 14 sur y Avenida San Claudio, Ciudad Universitaria, Col. San Manuel, Puebla, Pue., 72570, México

    Diego González & Luis Carlos Altamirano

Authors
  1. Diego González
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Luis Carlos Altamirano
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Centro de Investigación en Matemáticas, AC. (CIMAT), Area de Computación, Calle Jalisco S/N, Mineral de Valenciana, Guanajuato, CP 36250, Guanajuato, México

    Arturo Hernández Aguirre

  2. Ciencias de la Computación, Tecnológico de Monterrey, Campus Estado de México, Carretera al lago de Guadalupe Km 3,5, Col. Margarita Maza de Juárez, Atizapán de Zaragoza,, CP 52926, Estado de México, México

    Raúl Monroy Borja

  3. Instituto Nacional de Astrofísica, Optica y Electrónica (INAOE), Ciencias Computacionales, Luis Enrique Erro No. 1, Santa María Tonantzintla, CP 72840, Puebla, México

    Carlos Alberto Reyes Garciá

Rights and permissions

Reprints and permissions

Copyright information

© 2009 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

González, D., Altamirano, L.C. (2009). Quasi-invariant Illumination Recognition for Appearance-Based Models, Taking Advantage of Manifold Information and Non-uniform Sampling. In: Aguirre, A.H., Borja, R.M., Garciá, C.A.R. (eds) MICAI 2009: Advances in Artificial Intelligence. MICAI 2009. Lecture Notes in Computer Science(), vol 5845. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-05258-3_24

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-05258-3_24

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-05257-6

  • Online ISBN: 978-3-642-05258-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation