Local invariant feature-based methods such as SIFT have been proven highly effective for object recognition. However, they have made either relatively little use or too complex use of geometric constraints and are confounded when the detected features are superabundant. Here we make two contributions aimed at overcoming these problems. First, we rank the SIFT points (R-SIFT) using visual saliency. Second, we use the reduced set of R-SIFT features to construct a class specific hyper graph (CSHG) which comprehensively utilizes local SIFT and global geometric constraints. Moreover, it efficiently captures multiple object appearance instances. We show how the CSHG can be learned from example images for objects of a particular class. Experiments reveal that the method gives excellent recognition performance, with a low false-positive rate.


  1. 1.
    Bosch, A., Zisserman, A., Muoz, X.: Scene Classification Using a Hybrid Generative/Discriminative Approach. IEEE Trans. PAMI 30(4), 1–16 (2008)CrossRefGoogle Scholar
  2. 2.
    Bosch, A., Muoz, X., Marti, R.: Which is the best way to organize/classify images by content? Image and Vision Computing 25, 778–791 (2007)CrossRefGoogle Scholar
  3. 3.
    Berge, C.: Hypergraphs. North-Holland, Amsterdam (1989)zbMATHGoogle Scholar
  4. 4.
    Chung, F.: Spectral Graph Theory. American Mathematical Society (1997)Google Scholar
  5. 5.
    Lowe, D.G.: Distinctive image features from scale-invariant key points. IJCV 60(2), 91–110 (2004)CrossRefGoogle Scholar
  6. 6.
    Elazary, L., Itti, L.: Interesting objects are visually salient. Journal of Vision 8(3), 1–15 (2008)CrossRefGoogle Scholar
  7. 7.
    Li, F.F., Perona, P.: A Bayesian hierarchical model for learning natural scene categories. CVPR 2, 524–531 (2005)Google Scholar
  8. 8.
    Bay, H., Tuytelaars, T., Gool, L.V.: SURF: Speeded Up Robust Features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 404–417. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  9. 9.
    Zhang, J., Marszablek, M., Lazebnik, S., Schmid, C.: Local Features and Kernels for Classification of Texture and Object Categories. IJCV 73(2), 213–238 (2007)CrossRefGoogle Scholar
  10. 10.
    Yan, K., Sukthankar, R.: PCA-SIFT: A more distinctive representation for local image descriptors. CVPR (2), 506–513 (2004)Google Scholar
  11. 11.
    Schonemann, P.: A generalized solution of the orthogonal Procrustes problem. Psychometrika 31, 1–10 (1966)MathSciNetCrossRefzbMATHGoogle Scholar
  12. 12.
    Sivic, J., Zisserman, A.: VideoGoogle: A text retrieval approach to object matching in videos. ICCV 2, 1470–1477 (2003)Google Scholar
  13. 13.
    Sivic, J., Russell, B.C., Efros, A.A., Zisserman, A., Freeman, W.T.: Discovering objects and their location in images. ICCV 1, 370–378 (2005)Google Scholar
  14. 14.
    Torsello, A., Hancock, E.R.: Graph Embedding using Tree Edit Union. Pattern Recognition 40, 1393–1405 (2007)CrossRefzbMATHGoogle Scholar
  15. 15.
    Torsello, A., Hancock, E.R.: Learning Shape Classes using a Mixture of Tree Union. IEEE Trans. PAMI 28, 954–967 (2006)CrossRefGoogle Scholar
  16. 16.
    Bonev, B., Escolano, F., Lozano, M.A., Suau, P., Cazorla, M.A., Aguilar, W.: Constellations and the Unsupervised Learning of Graphs. In: Escolano, F., Vento, M. (eds.) GbRPR. LNCS, vol. 4538, pp. 340–350. Springer, Heidelberg (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Shengping Xia
    • 1
    • 2
  • Edwin R. Hancock
    • 2
  1. 1.ATR Lab, School of Electronic Science and EngineeringNational University of Defense TechnologyChangshaP.R. China
  2. 2.Department of Computer ScienceUniversity of YorkYorkUK

Personalised recommendations