Grouping of Semantically Similar Image Positions

  • Lutz Priese
  • Frank Schmitt
  • Nils Hering
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5575)


Features from the Scale Invariant Feature Transformation (SIFT) are widely used for matching between spatially or temporally displaced images. Recently a topology on the SIFT features of a single image has been introduced where features of a similar semantics are close in this topology. We continue this work and present a technique to automatically detect groups of SIFT positions in a single image where all points of one group possess a similar semantics. The proposed method borrows ideas and techniques from the Color-Structure-Code segmentation method and does not require any user intervention.


Image analysis segmentation semantics SIFT 


  1. 1.
    Hering, N., Schmitt, F., Priese, L.: Image understanding using self-similar sift features. In: International Conference on Computer Vision Theory and Applications (VISAPP), Lisboa, Portugal (to be published, 2009)Google Scholar
  2. 2.
    Lowe, D.: Object recognition from local scale-invariant features. In: Proc. of the International Conference on Computer Vision ICCV, Corfu, pp. 1150–1157 (1999)Google Scholar
  3. 3.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 20, 91–110 (2003)Google Scholar
  4. 4.
    Rehrmann, V., Priese, L.: Fast and robust segmentation of natural color scenes. In: Chin, R.T., Pong, T.-C. (eds.) ACCV 1998. LNCS, vol. 1351, pp. 598–606. Springer, Heidelberg (1997)Google Scholar
  5. 5.
    Slot, K., Kim, H.: Keypoints derivation for object class detection with sift algorithm. In: Rutkowski, L., Tadeusiewicz, R., Zadeh, L.A., Żurada, J.M. (eds.) ICAISC 2006. LNCS, vol. 4029, pp. 850–859. Springer, Heidelberg (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Lutz Priese
    • 1
  • Frank Schmitt
    • 1
  • Nils Hering
    • 1
  1. 1.Institute for Computational VisualisticsUniversity Koblenz-LandauKoblenzGermany

Personalised recommendations