Spatially-Sensitive Affine-Invariant Image Descriptors

  • Alexander M. Bronstein
  • Michael M. Bronstein
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6312)


Invariant image descriptors play an important role in many computer vision and pattern recognition problems such as image search and retrieval. A dominant paradigm today is that of “bags of features”, a representation of images as distributions of primitive visual elements. The main disadvantage of this approach is the loss of spatial relations between features, which often carry important information about the image. In this paper, we show how to construct spatially-sensitive image descriptors in which both the features and their relation are affine-invariant. Our construction is based on a vocabulary of pairs of features coupled with a vocabulary of invariant spatial relations between the features. Experimental results show the advantage of our approach in image retrieval applications.


Image Retrieval Visual Word Spatial Relation Retrieval Performance Image Descriptor 
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.
    Lindeberg, T.: Feature detection with automatic scale selection. IJCV 30, 79–116 (1998)CrossRefGoogle Scholar
  2. 2.
    Mikolajczyk, K., Schmid, C.: Indexing based on scale invariant interest points. In: Proc. ICCV., vol. 1, pp. 525–531 (2001)Google Scholar
  3. 3.
    Lowe, D.: Distinctive image features from scale-invariant keypoint. IJCV (2004)Google Scholar
  4. 4.
    Mikolajczyk, K., Schmid, C.: Scale & affine invariant interest point detectors. IJCV 60, 63–86 (2004)CrossRefGoogle Scholar
  5. 5.
    Tuytelaars, T., Van Gool, L.: Matching widely separated views based on affine invariant regions. IJCV 59, 61–85 (2004)CrossRefGoogle Scholar
  6. 6.
    Kadir, T., Zisserman, A., Brady, M.: An affine invariant salient region detector. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3021, pp. 228–241. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  7. 7.
    Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide-baseline stereo from maximally stable extremal regions. Image and Vision Computing 22, 761–767 (2004)CrossRefGoogle Scholar
  8. 8.
    Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., Gool, L.: A comparison of affine region detectors. IJCV 65, 43–72 (2005)CrossRefGoogle Scholar
  9. 9.
    Bay, H., Tuytelaars, T., Van Gool, L.: Surf: Speeded up robust features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, p. 404. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  10. 10.
    Sivic, J., Zisserman, A.: Video google: A text retrieval approach to object matching in videos. In: Proc. CVPR (2003)Google Scholar
  11. 11.
    Chum, O., Philbin, J., Sivic, J., Isard, M., Zisserman, A.: Total recall: Automatic query expansion with a generative feature model for object retrieval. In: Proc. ICCV (2007)Google Scholar
  12. 12.
    Shechtman, E., Irani, M.: Matching local self-similarities across images and videos. In: Proc. CVPR, pp. 1–8 (2007)Google Scholar
  13. 13.
    Marszaek, M., Schmid, C.: Spatial weighting for bag-of-features. In: Proc. CVPR., vol. 2 (2006)Google Scholar
  14. 14.
    Leibe, B., Leonardis, A., Schiele, B.: Combined object categorization and segmentation with an implicit shape model. In: Workshop on Statistical Learning in Computer Vision, ECCV, pp. 17–32 (2004)Google Scholar
  15. 15.
    Grauman, K., Darrell, T.: Efficient image matching with distributions of local invariant features. In: Proc. CVPR., vol. 2 (2005)Google Scholar
  16. 16.
    Rubner, Y., Tomasi, C., Guibas, L.: The earth mover’s distance as a metric for image retrieval. IJCV 40, 99–121 (2000)zbMATHCrossRefGoogle Scholar
  17. 17.
    Nister, D., Stewenius, H.: Scalable recognition with a vocabulary tree. In: Proc. CVPR (2006)Google Scholar
  18. 18.
    Wu, Z., Ke, Q., Isard, M., Sun, J.: Bundling features for large-scale partial-duplicate web image search. In: Proc. CVPR (2009)Google Scholar
  19. 19.
    Sivic, J., Zisserman, A.: Video data mining using configurations of viewpoint invariant regions. In: Proc. CVPR (2004)Google Scholar
  20. 20.
    Sivic, J., Russell, B., Efros, A., Zisserman, A., Freeman, W.: Discovering object categories in image collections. In: Proc. ICCV., vol. 2 (2005)Google Scholar
  21. 21.
    Chum, O., Matas, J.: Geometric hashing with local affine frames. In: Proc. CVPR (2006)Google Scholar
  22. 22.
    Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: Proc. CVPR., vol. 2 (2006)Google Scholar
  23. 23.
    Amores, J., Sebe, N., Radeva, P.: Context-based object-class recognition and retrieval by generalized correlograms. IEEE Trans. PAMI 29, 1818–1833 (2007)Google Scholar
  24. 24.
    Ovsjanikov, M., Bronstein, A.M., Bronstein, M.M., Guibas, L.: Shape google: a computer vision approach to invariant shape retrieval. In: Proc. NORDIA (2009)Google Scholar
  25. 25.
    Behmo, R., Paragios, N., Prinet, V.: Graph commute times for image representation. In: Proc. CVPR (2008)Google Scholar
  26. 26.
    Forssén, P., Lowe, D.: Shape descriptors for maximally stable extremal regions. In: Proc. ICCV, pp. 59–73 (2007)Google Scholar
  27. 27.
    Muse, P., Sur, F., Cao, F., Lisani, J.L., Morel, J.M.: A theory of shape identification (2005)Google Scholar
  28. 28.
    Bronstein, A.M., Bronstein, M.M.: Affine-invariant spatial vocabularies. Technical Report Techn. Report CIS-2009-10, Dept. of Computer Science, Technion, Israel (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Alexander M. Bronstein
    • 1
    • 2
  • Michael M. Bronstein
    • 1
    • 3
  1. 1.BBK Technologies ltd 
  2. 2.Dept. of Electrical EngineeringTel Aviv University 
  3. 3.Dept. of Computer Science, TechnionIsrael Institute of Technology 

Personalised recommendations