Detecting and Ranking Saliency for Scene Description

  • William D. Ferreira
  • Díbio L. Borges
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3287)

Abstract

There is a long tradition in Computational Vision research regarding Vision as an information processing task which builds up from low level image features to high level reasoning functions. As far as low level image detectors are concerned there is a plethora of techniques found in the literature, although many of them especially designed for particular applications. For natural scenes, where objects and backgrounds change frequently, finding regions of interest which were triggered by a concentration of non-accidental properties can provide a more informative and stable intermediate mechanism for scene description than just low level features. In this paper we propose such a mechanism to detect and rank salient regions in natural and cluttered images. First, a bank of Gabor filters is applied to the image in a variety of directions. The most prominent directions found are then selected as primitive features. Starting from the selected directions with largest magnitudes a resultant is computed by including directional features in the image neighborhood. The process stops when inclusion of other points in the region makes the resultant direction change significantly from the initial one. This resultant is the axis of symmetry of that salient region. A rank is built showing in order the salient regions found in a scene. We report results on natural images showing a promising line of research for scene description and visual attention.

Keywords

Visual Attention Natural Image Directional Feature Salient Region Saliency 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.
Download to read the full conference paper text

References

  1. 1.
    Carreira, M., Mirmehdi, M., Thomas, B., Haddon, J.: Grouping of Directional Features using an Extended Hough Transform. In: Proc. of Int. Conf. on Pattern Recognition (ICPR), pp. 990–993 (2000)Google Scholar
  2. 2.
    Dimai, A.: Invariant Scene Description based on Salient Regions for Preattentive Similarity Assessment. In: Proc. of Int. Conf. on Image Analysis and Processing (ICIAP), pp. 957–962 (1999)Google Scholar
  3. 3.
    Hubel, D.: Eye, Brain, and Vision. W. H. Freeman and Company, USA (1995)Google Scholar
  4. 4.
    Kadir, T., Brady, M.: Saliency, Scale and Image Description. Int. Journal of Computer Vision 45(2), 83–105 (2001)MATHCrossRefGoogle Scholar
  5. 5.
    Kosslyn, S.: Image and Brain. MIT Press, USA (1994)Google Scholar
  6. 6.
    Luo, J., Singhal, A.: On Measuring Low-Level Saliency in Photographic Images. In: Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 1084–1089 (2000)Google Scholar
  7. 7.
    Marr, D.: Vision: A Computational Investigation into the Human Representation and Processing of Visual Information. W. H. Freeman and Company, USA (1982)Google Scholar
  8. 8.
    Reisfeld, D., Wolfson, H., Yeshrun, Y.: Context Free Attentional Operators: the Generalized Symmetry Transform. Int. Journal of Computer Vision 14, 114–130 (1995)CrossRefGoogle Scholar
  9. 9.
    Schmid, C., Mohr, R., Bauckhage, C.: Evaluation of Interest Point Detectors. Int. Journal of Computer Vision 37(2), 151–172 (2000)MATHCrossRefGoogle Scholar
  10. 10.
    Slowe, T., Marsic, I.: Saliency-based Visual Representation for Compression. In: Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 554–557 (1997)Google Scholar
  11. 11.
    Ullman, S.: High-level Vision. MIT Press, USA (1996)MATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • William D. Ferreira
    • 1
  • Díbio L. Borges
    • 1
  1. 1.Laboratory for Vision and Image SciencePontifical Catholic University of Paraná (PUCPR)CuritibaBrazil

Personalised recommendations