Generation of N-Parametric Appearance-Based Models Through Non-uniform Sampling

  • Luis Carlos Altamirano
  • Leopoldo Altamirano Robles
  • Matías Alvarado
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3287)

Abstract

In this work, a generalization of non-uniform sampling technique to construct appearance-based models is proposed. This technique analyses the object appearance defined by several parameters of variability, determining how many and which images are required to model appearance, with a given precision ε. Throughout non-uniform sampling, we obtain a guideline to spend less time on model construction and to diminish storage, when pose estimation no matters. The proposed technique is based on a scheme of N-linear interpolation and SSD (Sum-of-Squared-Difference) distance, and it is used in conjunction with the eigenspaces method for object recognition. Experimental results showing the advantages are exposed.

References

  1. 1.
    Murase, H., Nayar, S.K.: Visual learning and recognition of 3-D objects from appearance. International Journal of Computer Vision 14(1), 5–24 (1995)CrossRefGoogle Scholar
  2. 2.
    Nelson, R.C., Selinger, A.: Experiments on (Intelligent) Brute Force Methods for Appearance- Based Object Recognition. In: DARPA Image Unders. Worksh., pp. 1197–1205 (1997)Google Scholar
  3. 3.
    Pauli, J., Benkwitz, M., Sommer, G.: RBF Networks Appearance-Based Object Detection. In: Proceedings of ICANN, Paris, vol. 1, pp. 359–364 (1995)Google Scholar
  4. 4.
    Poggio, T., Beymer, D.: Regularization Networks for Visual Learning. In: Early Visual Learning, Oxford University Press, Oxford (1996)Google Scholar
  5. 5.
    Moghaddam, B., Pentland, A.: Probabilistic visual learning for object representation. In: Early Visual Learning, Oxford University Press, Oxford (1996)Google Scholar
  6. 6.
    Belhumeur, P.N., Kriegman, D.J.: What is the Set of Images of an Object Under All Possible Ilumination Conditions? Int. J. C. Vision 28(3), 245–260 (1998)CrossRefGoogle Scholar
  7. 7.
    Epstein, R., Hallinan, P., Yuille, A.: 5±2 Eigenimages suffice: An empirical investigation of low-dimensional lighting models. In: Proc. IEEE Worksh. on physics-based modeling in computer vision (1995)Google Scholar
  8. 8.
    Glassner, A.S.: Principles of digital image synthesis. Morgan-Kaufmann Pub., San Francisco (2000)Google Scholar
  9. 9.
    Seitz, S.M., Dyer, C.R.: Photorealistic Scene Reconstruction by Voxel Coloring. Int. Journal of Computer Vision 35(2) (1999)Google Scholar
  10. 10.
    Epstein, R., Yuille, A.L., Belhumeur, P.N.: Learning Object Representations from Lighting Variations. In: Buxton, B.F., Cipolla, R. (eds.) ECCV 1996. LNCS, vol. 1065, Springer, Heidelberg (1996)Google Scholar
  11. 11.
    Koenderink, J.J., Van Doorn, A.J.: The internal representation of solid shape with respect to vision. Biological Cybernetics 32 (1979)Google Scholar
  12. 12.
    Cootes, T.F., Wheeler, G.V., Walker, K.N., Taylor, C.J.: Coupled-View Active Appearance Models. In: The Eleventh British Mach. Vis. Conf. U. of Bristol (2000)Google Scholar
  13. 13.
    Mokhtarian, F., Abbasi, S.: Automatic Selection of Optimal Views in Multi-view Object Recognition. In: The Eleventh British Mach. Vis. Conf., U. of Bristol (2000)Google Scholar
  14. 14.
    Altamirano, L.C., Altamirano, L., Alvarado, M.: Non-Uniform Sampling For Improved Appearance- Based Models. Pattern Rec. Letters 24(1-3), 529–543 (2003)Google Scholar
  15. 15.
    Marsden, J.E., Tromba, A.J.: Vector Calculus. W.H. Freeman and Co., New York (1976)MATHGoogle Scholar
  16. 16.
    Nayar, S., Murase, H., Nene, S.: Parametric Appearance Representation. In: Early Visual Learning, Oxford University Press, Oxford (1996)Google Scholar
  17. 17.
    Farin, G.: Curves and Surfaces for Computer Aided Geometric Design. A. Press, Inc., New York (1988)MATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Luis Carlos Altamirano
    • 1
  • Leopoldo Altamirano Robles
    • 2
  • Matías Alvarado
    • 1
  1. 1.Instituto Mexicano del PetróleoPIMAyCSan Bartolo Atepehuacán
  2. 2.Instituto Nacional de Astrofísica, Óptica y ElectrónicaPueblaMéxico

Personalised recommendations