An Affine Invariant Salient Region Detector

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3021)


In this paper we describe a novel technique for detecting salient regions in an image. The detector is a generalization to affine invariance of the method introduced by Kadir and Brady [10]. The detector deems a region salient if it exhibits unpredictability in both its attributes and its spatial scale.

The detector has significantly different properties to operators based on kernel convolution, and we examine three aspects of its behaviour: invariance to viewpoint change; insensitivity to image perturbations; and repeatability under intra-class variation. Previous work has, on the whole, concentrated on viewpoint invariance. A second contribution of this paper is to propose a performance test for evaluating the two other aspects.

We compare the performance of the saliency detector to other standard detectors including an affine invariance interest point detector. It is demonstrated that the saliency detector has comparable viewpoint invariance performance, but superior insensitivity to perturbations and intra-class variation performance for images of certain object classes.


Object Class Region Detector Saliency Detector Sampling Window Background Clutter 
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.
    Agarwal, S., Roth, D.: Learning a sparse representation for object detection. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2353, pp. 113–130. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  2. 2.
    Baumberg, A.: Reliable feature matching across widely separated views. In: Proc. Computer Vision Pattern Recognition, pp. 774–781 (2000)Google Scholar
  3. 3.
    Borenstein, E., Ullman, S.: Class-specific, top-down segmentation. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2351, pp. 109–124. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  4. 4.
    Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: Proc. Computer Vision Pattern Recognition, pp. II: 264–271 (2003)Google Scholar
  5. 5.
    Foley, J.A., Van Dam, A.: Fundamentals of Interactive Computer Graphics. Addison-Wesley, Reading (1982)Google Scholar
  6. 6.
    Griffin, L.D.: Scale-imprecision space. Image and Vision Computing 15, 369–398 (1997)CrossRefGoogle Scholar
  7. 7.
    Harris, C., Stephens, M.: A combined corner and edge detector. In: Proc. Alvey Vision Conf., Manchester, pp. 189–192 (1988)Google Scholar
  8. 8.
    Kadir, T.: Scale, Saliency and Scene Description. PhD thesis, University of Oxford (2002)Google Scholar
  9. 9.
    Kadir, T., Boukerroui, D., Brady, J.M.: An analysis of the scale saliency algorithm. Technical Report OUEL No: 2264/03, University of Oxford (2003)Google Scholar
  10. 10.
    Kadir, T., Brady, J.M.: Scale, saliency and image description. Intl. J. of Computer Vision 45(2), 83–105 (2001)zbMATHCrossRefGoogle Scholar
  11. 11.
    Koenderink, J.J., van Doorn, A.J.: Representation of local geometry in the visual system. Biological Cybernetics 63, 291–297 (1987)CrossRefGoogle Scholar
  12. 12.
    Koenderink, J.J., van Doorn, A.J.: The structure of locally orderless images. Intl. J. of Computer Vision 31(2/3), 159–168 (1999)CrossRefGoogle Scholar
  13. 13.
    Kok-Wiles, S., Brady, M., Highnam, R.: Comparing mammogram pairs for the detection of lesions. In: Proc. Intl. Workshop on Digital Mammography, pp. 103–110 (1998)Google Scholar
  14. 14.
    Lindeberg, T.: Detecting salient blob-like image structures and their scales with a scale-space primal sketch: A method for focus-of-attention. Intl. J. of Computer Vision 11(3), 283–318 (1993)CrossRefGoogle Scholar
  15. 15.
    Lindeberg, T., ter Haar Romeny, B.M.: Linear scale-space: I. basic theory, II. early visual operations. In: ter Haar Romeny, B.M. (ed.) Geometry-Driven Diffusion, Kluwer Academic Publishers, Dordrecht (1994)Google Scholar
  16. 16.
    Lowe, D.G.: Object recognition from local scale-invariant features. In: Proc. Intl. Conf. on Computer Vision, pp. 1150–1157 (1999)Google Scholar
  17. 17.
    Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. In: Proc. British Machine Vision Conf., pp. 384–393 (2002)Google Scholar
  18. 18.
    Mikolajczyk, K., Schmid, C.: Indexing based on scale invariant interest points. In: Proc. Intl. Conf. on Computer Vision (2001)Google Scholar
  19. 19.
    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
  20. 20.
    Schaffalitzky, F., Zisserman, A.: Multi-view matching for unordered image sets, or “How do I organize my holiday snaps?”. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 414–431. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  21. 21.
    Schmid, C., Mohr, R.: Local greyvalue invariants for image retrieval. IEEE Trans. Pattern Analysis and Machine Intelligence 19(5), 530–535 (1997)CrossRefGoogle Scholar
  22. 22.
    Tuytelaars, T., Van Gool, L.: Wide baseline stereo based on local, affinely invariant regions. In: Proc. British Machine Vision Conf., pp. 412–422 (2000)Google Scholar
  23. 23.
    Weber, M., Welling, M., Perona, P.: Unsupervised learning of models for recognition. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1842, pp. 18–32. Springer, Heidelberg (2000)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  1. 1.Department of Engineering ScienceUniversity of OxfordOxfordUK

Personalised recommendations