Keypoint-Based Detection of Near-Duplicate Image Fragments Using Image Geometry and Topology

  • Mariusz Paradowski
  • Andrzej Śluzek
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6375)


One of the advanced techniques in visual information retrieval is detection of near-duplicate fragments, where the objective is to identify images containing almost exact copies of unspecified fragments of a query image. Such near-duplicates would typically indicate the presence of the same object in images. Thus, the assumed differences between near-duplicate fragments should result either from image-capturing settings (illumination, viewpoint, camera parameters) or from the object’s deformation (e.g. location changes, elasticity of the object, etc.). The proposed method of near-duplicate fragment detection exploits statistical properties of keypoint similarities between compared images. Two cases are discussed. First, we assume that near-duplicates are (approximately) related by affine transformations, i.e. the underlying objects are locally planar. Secondly, we allow more random distortions so that a wider range of objects (including deformable ones) can be considered. Thus, we exploit either the image geometry or image topology. Performances of both approaches are presented and compared.


Query Image Planar Object Image Geometry Image Fragment Keypoint Detector 
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.
    Cheng, X., Hu, Y., Chia, L.-T.: Image near-duplicate retrieval using local dependencies in spatial-scale space. In: Proc. 16th ACM ICM, pp. 627–630 (2008)Google Scholar
  2. 2.
    Zhao, W.-L., Ngo, C.-W., Tan, H.-K., Wu, X.: Near-duplicate keyframe identification with interest point matching and pattern learning. IEEE Transactions on Multimedia 9(5), 1037–1048 (2007)CrossRefGoogle Scholar
  3. 3.
    Heritier, M., Foucher, S., Gagnon, L.: Key-places detection and clustering in movies using latent aspects. In: Proc. 14th IEEE Int. Conf. IP, vol. 2, pp. II.225–II.228 (2007)Google Scholar
  4. 4.
    Zhao, W.-L., Ngo, C.-W.: Scale-rotation invariant pattern entropy for keypoint-based near-duplicate detection. IEEE Trans. on IP 18(2), 412–423 (2009)Google Scholar
  5. 5.
    Tuytelaars, T., Mikolajczyk, K.: Local invariant feature detectors: a survey. Foundations & Trends in Computer Graphics & Vision 3(3), 177–280 (2007)CrossRefGoogle Scholar
  6. 6.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. Int. J. Comp. Vision 60(2), 91–110 (2004)CrossRefGoogle Scholar
  7. 7.
    Bay, H., Ess, A., Tuytelaars, T., Van Gool, L.: Speeded-up robust features (SURF). Comp. Vision & Image Understanding 110(3), 346–359 (2008)CrossRefGoogle Scholar
  8. 8.
    Paradowski, M., Śluzek, A.: Matching planar fragments of images using histograms of decomposed affine transforms (unpublished 2009)Google Scholar
  9. 9.
    Xiao, J., Shah, M.: Two-frame wide baseline matching. In: Proc. 9th IEEE Int. Conf. on Computer Vision, pp. 603–609 (2003)Google Scholar
  10. 10.
    Paradowski, M., Śluzek, A.: Detection of image fragments related by affine transforms: matching triangles and ellipses. In: Proc. of ICISA 2010, vol. 1, pp. 189–196 (2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Mariusz Paradowski
    • 1
    • 3
  • Andrzej Śluzek
    • 2
    • 3
  1. 1.Institute of InformaticsWrocław University of TechnologyPoland
  2. 2.Faculty of Physics, Astronomy and InformaticsNicolaus Copernicus UniversityToruńPoland
  3. 3.School of Computer EngineeringNanyang Technological UniversitySingapore

Personalised recommendations