Object Recognition by Combining Appearance and Geometry

  • David Crandall
  • Pedro Felzenszwalb
  • Daniel Huttenlocher
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4170)


We present a new class of statistical models for part-based object recognition. These models are explicitly parametrized according to the degree of spatial structure that they can represent. This provides a way of relating different spatial priors that have been used in the past such as joint Gaussian models and tree-structured models. By providing explicit control over the degree of spatial structure, our models make it possible to study questions such as the extent to which additional spatial constraints among parts are helpful in detection and localization, and the tradeoff between representational power and computational cost. We consider these questions for object classes that have substantial geometric structure, such as airplanes, faces and motorbikes, using datasets employed by other researchers to facilitate evaluation. We find that for these classes of objects, a relatively small amount of spatial structure in the model can provide statistically indistinguishable recognition performance from more powerful models, and at a substantially lower computational cost.


Object Recognition Training Image Object Class Maximal Clique Appearance Model 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Amit, Y.: 2D Object Detection and Recognition, Models, Algorithms, and Networks. MIT Press, Cambridge (2002)Google Scholar
  2. 2.
    Amit, Y., Trouvé, A.: Pop: Patchwork of parts models for object recognition (2005)Google Scholar
  3. 3.
    Bertele, U., Brioschi, F.: Nonserial Dynamic Programming. Academic Press, London (1972)MATHGoogle Scholar
  4. 4.
    Burl, M.C., Perona, P.: Recognition of planar object classes. In: IEEE Conference on Computer Vision and Pattern Recognition (1996)Google Scholar
  5. 5.
    Burl, M.C., Weber, M., Perona, P.: A probabilistic approach to object recognition using local photometry and global geometry. In: Burkhardt, H., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1407. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  6. 6.
    Carlsson, S.: Geometric structure and view invariant recognition. Phil. Trans. R. Soc. Lond. A 359 (1740) (1998)Google Scholar
  7. 7.
    Cowell, R.F., Dawid, A.P., Lauritzen, S.L., Spiegelhalter, D.J.: Probabilistic Networks and Expert Systems. Springer, Heidelberg (1999)MATHGoogle Scholar
  8. 8.
    DeLong, E.R., DeLong, D.M., Clarke-Pearson, D.L.: Comparing the areas under two or more correlated roc curves: a non-parametric approach. Biometrics 44(3) (1998)Google Scholar
  9. 9.
    Felzenszwalb, P.F., Huttenlocher, D.P.: Distance transforms of sampled functions, Cornell Computing and Information Science Technical Report TR2004-1963 (September 2004)Google Scholar
  10. 10.
    Felzenszwalb, P.F., Huttenlocher, D.P.: Pictorial structures for object recognition. International Journal of Computer Vision 61(1) (2005)Google Scholar
  11. 11.
    Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: IEEE Conference on Computer Vision and Pattern Recognition (2003)Google Scholar
  12. 12.
    Fischler, M.A., Elschlager, R.A.: The representation and matching of pictorial structures. IEEE Transactions on Computer 22(1) (1973)Google Scholar
  13. 13.
    Huttenlocher, D.P., Ullman, S.: Recognizing solid objects by alignment with an image. International Journal of Computer Vision 5(2), 195–212 (1990)CrossRefGoogle Scholar
  14. 14.
    Ioffe, S., Forsyth, D.A.: Probabilistic methods for finding people. International Journal of Computer Vision 43(1) (2001)Google Scholar
  15. 15.
    Lipson, P., Grimson, E., Sinha, P.: Configuration based scene classification and image indexing. In: IEEE Conference on Computer Vision and Pattern Recognition (1997)Google Scholar
  16. 16.
    Rose, D.J.: On simple characterizations of k-trees. Discrete Mathematics 7(3-4), 317–322 (1974)MATHCrossRefMathSciNetGoogle Scholar
  17. 17.
    Schneiderman, H., Kanade, T.: Probabilistic formulation for object recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (1998)Google Scholar
  18. 18.
    Wells III., W.M.: Efficient synthesis of Gaussian filters by cascaded uniform filters. IEEE Transactions on Pattern Analysis and Machine Intelligence 8(2) (1986)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • David Crandall
    • 1
  • Pedro Felzenszwalb
    • 2
  • Daniel Huttenlocher
    • 1
  1. 1.Cornell UniversityIthacaUSA
  2. 2.The University of ChicagoChicagoUSA

Personalised recommendations