Deformable Object Matching Based on Multi-scale Local Histograms

  • N. Pérez de la Blanca
  • J. M. Fuertes
  • M. Lucena
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3179)


This paper presents a technique to enable deformable objects to be matched throughout video sequences based on the information provided by the multi-scale local histograms of the images. We shall show that this technique is robust enough for viewpoint changes, lighting changes, large motions of the matched object and small changes in rotation and scale. Unlike other well-known color-based techniques, this technique only uses the gray level values of the image. The proposed algorithm is mainly based on the definition of a particular multi-scale template model and a similarity measure for histogram matching.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Agarwal, S., Roth, D.: Learning a sparse representation for object detection. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2353, pp. 113–130. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  2. 2.
    Birgé, L., Rozenholc, Y.: How many bins should be put in a regular histogram. Technical Report 721. Laboratoire de Probabilités et Modèles Aléatoires, CNRS-UMR 7599, Université Paris VI & Université Paris VII (2002)Google Scholar
  3. 3.
    Hadjidemetriou, E., Grossberg, M.D., Nayar, S.K.: Spatial information in multiresolution histograms. In: Intern. Conf. CVPR 2001 (2001)Google Scholar
  4. 4.
    Heisele, B., Ho, P., Wu, J., Poggio, T.: Face recognition: component-based versus global approaches. Computer Vision and Image Understanding 91, 6–21 (2003)CrossRefGoogle Scholar
  5. 5.
    Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scaleinvariant learning. In: IEEE CVPR 2003, pp. 264–271 (2003)Google Scholar
  6. 6.
    Griffin, L.D.: Scale-imprecission space. Image and Vision Computing 15, 369–398 (1999)CrossRefGoogle Scholar
  7. 7.
    Koenderink, J.J., Van Doorn, A.J.: The Structure of locally orderless images. Intern. Journal of Computer Vision 318273, 159–168 (1999)Google Scholar
  8. 8.
    Kadir, T., Brady, M.: Scale, saliency and image description. Intern. Journal of Computer Vision 45(2), 83–105 (2001)MATHCrossRefGoogle Scholar
  9. 9.
    Lowe, D.G.: Object recognition from local scale-invariant features. In: ICCV 1999, pp. 1150–1157 (1999)Google Scholar
  10. 10.
    Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. In: BMCV 2002 Conference, pp. 384–393 (2002)Google Scholar
  11. 11.
    Mikolajczyk, K., Schmid, C.: An affine invariant interest point detector. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 128–142. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  12. 12.
    Niblack, W.: The QBIC project: Querying images by content using color, texture and shape. In: Proc. Of SPIE Conf. on Storage and Retrieval for image and video database, vol. 1908, pp. 173–187 (1993)Google Scholar
  13. 13.
    Schiele, B., Crowley, J.L.: Object recognition using multidimensional receptive field histograms. In: ECCV 1996, vol. I, pp. 610–619 (1996)Google Scholar
  14. 14.
    Schiele, B., Crowley, J.L.: Robustness of object recognition to view point changes using multidimensional receptive fields histograms. ECIS-VAP (1996)Google Scholar
  15. 15.
    Swain, M.J., Ballard, D.H.: Color Indexing Intern. Journal of Computer Vision 7(1), 11–32 (1991)CrossRefGoogle Scholar
  16. 16.
    Topsoe, F.: Some inequalities for information divergence and related measures of discrimination. IEEE Trans. Information Theory IT-46, 1602–1609 (2000)CrossRefMathSciNetGoogle Scholar
  17. 17.
    Tuytelaars, T., Van Gool, L.: Wide baseline stereo based on local affinely invariant regions. In: British Machine Vision Conference, Bristol, U.K., pp. 412–422 (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • N. Pérez de la Blanca
    • 1
  • J. M. Fuertes
    • 2
  • M. Lucena
    • 2
  1. 1.Department of Computer Science and Artificial Intelligence, ETSIIUniversity of GranadaGranadaSpain
  2. 2.Departmento de Informática. Escuela Politécnica SuperiorUniversidad de JaénJaénSpain

Personalised recommendations