Detecting Distinguished Regions by Saliency

  • Friedrich Fraundorfer
  • Horst Bischof
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2749)


A method for detecting and characterizing local image regions based on saliency is introduced. The proposed method detects scale localized salient regions in an image by a saliency operator which uses the concept of visual attention. A new descriptor based on a corner-ness measure is presented which allows a stable identification of regions of interest and at the same time allows for an elaborate description of the identified salient regions. Experiments demonstrate that the resulting salient regions and their descriptions are discriminative enough for image matching.


Visual Attention Image Match Salient Region Saliency Detector Point Correspondence 
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.


  1. 1.
    Schmid, C., Mohr, R.: Local grayvalue invariants for image retrieval. IEEE Trans. on Pattern Analysis and Machine Intelligence 19 (1997) 530–535CrossRefGoogle Scholar
  2. 2.
    Lowe, D.: Object recognition from local scale invariant features. In: ICCV. (1999) 1150–1157Google Scholar
  3. 3.
    Schaffalitzky, F., Zisserman, A.: Viewpoint invariant texture matching and wide baseline stereo. In: Proc. 8th International Conference on Computer Vision, Vancouver, Canada. (2001)Google Scholar
  4. 4.
    Tuytelaars, T., Gool, L.V.: Wide baseline stereo matching based on local, affinely invariant regions. In: British Machine Vision Conference BMVC’2000. (2000)Google Scholar
  5. 5.
    Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. In: BMVC02. (2002) 3D and VideoGoogle Scholar
  6. 6.
    Harris, C., Stephens, M.: A combined corner and edge detector. In: Alvey Vision Conference. (1988)Google Scholar
  7. 7.
    Schmid, C., Mohr, R., Bauckhage, C.: Evaluation of interest point detectors. International Journal of Computer Vision 37 (2000) 151–172zbMATHCrossRefGoogle Scholar
  8. 8.
    Kadir, T., Brady, M.: Saliency, scale and image description. International Journal of Computer Vision 45 (2001) 83–105zbMATHCrossRefGoogle Scholar
  9. 9.
    Fraundorfer, F., Bischof, H.: Affine invariant region matching using geometric hashing of line structures. In: 27th Workshop of the Austrian Association for Pattern Recognition (OEAGM/AAPR) 2003, Laxenburg-Vienna, 2003. (2003)Google Scholar
  10. 10.
    Wolfson, H., Lamdan, Y.: Geometric hashing: A general and efficient model-based recognition scheme. In: ICCV88. (1988) 238–249Google Scholar
  11. 11.
    Manjunath, B., Ma, W.: Texture features for browsing and retrieval of image data. IEEE Trans. on Pattern Analysis and Machine Intelligence 18 (1996) 837–842CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Friedrich Fraundorfer
    • 1
  • Horst Bischof
    • 1
  1. 1.Computer Graphics and VisionGraz University of TechnologyAustria

Personalised recommendations