Evaluation of Gradient Vector Flow for Interest Point Detection

  • Julian Stöttinger
  • René Donner
  • Lech Szumilas
  • Allan Hanbury
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5358)


We present and evaluate an approach for finding local interest points in images based on the non-minima suppression of Gradient Vector Flow (GVF) magnitude. Based on the GVF’s properties it provides the approximate centers of blob-like structures or homogeneous structures confined by gradients of similar magnitude. It results in a scale and orientation invariant interest point detector, which is highly stable against noise and blur. These interest points outperform the state of the art detectors in various respects. We show that our approach gives a dense and repeatable distribution of locations that are robust against affine transformations while they outperform state of the art techniques in robustness against lighting changes, noise, rotation and scale changes. Extensive evaluation is carried out using the Mikolajcyzk framework for interest point detector evaluation.


Interest Point JPEG Compression Gradient Vector Flow Interest Point Detector Maximally Stable Extremal Region 
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.
    Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: CVPR, pp. 264–271 (2003)Google Scholar
  2. 2.
    Mikolajczyk, K., Schmid, C.: Scale and affine invariant interest point detectors. IJCV 60, 63–86 (2004)CrossRefGoogle Scholar
  3. 3.
    Harris, C., Stephens, M.: A combined corner and edge detection. In: AVC, pp. 147–151 (1988)Google Scholar
  4. 4.
    Mikolajczyk, K., Schmid, C.: Indexing based on scale invariant interest points. In: ICCV, pp. 525–531 (2001)Google Scholar
  5. 5.
    Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust Wide Baseline Stereo from Maximally Stable Extremal Regions. In: BMVC, pp. 384–393 (2002)Google Scholar
  6. 6.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. IJCV 60, 91–110 (2004)CrossRefGoogle Scholar
  7. 7.
    Loy, G., Zelinsky, A.: Fast radial symmetry for detecting points of interest. PAMI, 959–973 (2003)Google Scholar
  8. 8.
    Donner, R., Mičušík, B., Langs, G., Bischof, H.: Sparse MRF appearance models for fast anatomical structure localisation. In: Proc. BMVC (2007)Google Scholar
  9. 9.
    Xu, C., Prince, J.L.: Snakes, shapes, and gradient vector flow. In: PR (1998)Google Scholar
  10. 10.
    Mikolajczyk, K., Schmid, C.: An affine invariant interest point detector. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 128–142. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  11. 11.
    Lindeberg, T.: Feature detection with automatic scale selection. IJCV 30, 79–116 (1998)CrossRefGoogle Scholar
  12. 12.
    Stöttinger, J., Hanbury, A., Sebe, N., Gevers, T.: Do colour interest points improve image retrieval? In: ICIP, pp. 169–172 (2007)Google Scholar
  13. 13.
    Witkin, A.P.: Scale-space filtering. In: IJCAI, pp. 1019–1022 (1983)Google Scholar
  14. 14.
    Lindeberg, T.: Effective scale: A natural unit for measuring scale-space lifetime. In: ISRN KTH (January 1994)Google Scholar
  15. 15.
    Reisfeld, D., Wolfson, H., Yeshurun, Y.: Context free attentional operators: the generalized symmetry transform. JCV (1994)Google Scholar
  16. 16.
    Loy, G., Zelinsky, A.: A fast radial symmetry transform for detecting points of interest. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 358–368. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  17. 17.
    Horn, B., Schunck, B.: Determining optical flow. Artiflcial Intelligence 17, 185–204 (1981)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Julian Stöttinger
    • 1
  • René Donner
    • 1
    • 2
    • 3
  • Lech Szumilas
    • 4
  • Allan Hanbury
    • 1
  1. 1.PRIPVienna University of TechnologyAustria
  2. 2.ICGTechnical University GrazAustria
  3. 3.CIRVienna Medical UniversityAustria
  4. 4.ACINVienna University of TechnologyAustria

Personalised recommendations