Salient Regions for Query by Image Content

  • Jonathon S. Hare
  • Paul H. Lewis
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3115)


Much previous work on image retrieval has used global features such as colour and texture to describe the content of the image. However, these global features are insufficient to accurately describe the image content when different parts of the image have different characteristics. This paper discusses how this problem can be circumvented by using salient interest points and compares and contrasts an extension to previous work in which the concept of scale is incorporated into the selection of salient regions to select the areas of the image that are most interesting and generate local descriptors to describe the image characteristics in that region. The paper describes and contrasts two such salient region descriptors and compares them through their repeatability rate under a range of common image transforms. Finally, the paper goes on to investigate the performance of one of the salient region detectors in an image retrieval situation.


Image Retrieval Image Content Interest Point Query Image Salient Point 
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.
    Carson, C., Thomas, M., Belongie, S., Hellerstein, J.M., Malik, J.: Blobworld: Image segmentation using expectation-maximization and its application to image querying. In: Third International Conference on Visual Information Systems, Springer, Heidelberg (1999)Google Scholar
  2. 2.
    Itti, L., Koch, C.: Computational modelling of visual attention. Nat. Rev. Neurosci. 2, 194–203 (2001)CrossRefGoogle Scholar
  3. 3.
    Harris, C., Stephens, M.: A combined corner and edge detector. In: Mathews, M.M. (ed.) Proceedings of the 4th ALVEY vision conference, pp. 147–151. University of Mancheste, England (1988)Google Scholar
  4. 4.
    Shokoufandeh, A., Marsic, I., Dickinson, S.: View-based object recognition using saliency maps. Image Vis. Comput. 17, 445–460 (1999)CrossRefGoogle Scholar
  5. 5.
    Sebe, N., Tian, Q., Loupias, E., Lew, M., Huang, T.: Evaluation of salient point techniques. Image and Vision Computing 21, 1087–1095 (2003)CrossRefGoogle Scholar
  6. 6.
    Sebe, N., Lew, M.S.: Comparing salient point detectors. Pattern Recognition Letters 24, 89–96 (2003)zbMATHCrossRefGoogle Scholar
  7. 7.
    Kadir, T.: Scale, Saliency and Scene Description. PhD thesis, University of Oxford, Deptartment of Engineering Science, Robotics Research Group, University of Oxford, Oxford, UK (2001)Google Scholar
  8. 8.
    Kadir, T., Brady, M.: Saliency, scale and image description. Int. J. Comput. Vis. 45, 83–105 (2001)zbMATHCrossRefGoogle Scholar
  9. 9.
    Tuytelaars, T., Gool, L.V.: Content-based image retrieval based on local affinely invariant regions. In: Third International Conference on Visual Information Systems, pp. 493–500 (1999)Google Scholar
  10. 10.
    Sivic, J., Zisserman, A.: Video google: A text retrieval approach to object matching in videos. In: Internaional Conference on Computer Vision (2003)Google Scholar
  11. 11.
    Obdrzalek, S., Matas, J.: Image retrieval using local compact dct-based representation. In: DAGM-Symposium 2003, pp. 490–497 (2003)Google Scholar
  12. 12.
    Gilles, S.: Robust Description and Matching of Images. PhD thesis, University of Oxford (1998)Google Scholar
  13. 13.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. To appear in International Journal of Computer Vision (2004)Google Scholar
  14. 14.
    Lowe, D.: Object recognition from local scale-invariant features. In: Proc. of the International Conference on Computer Vision ICCV, Corfu, pp. 1150–1157 (1999)Google Scholar
  15. 15.
    Marr, D.: VISION: A computational Investigation into Human Represenation and Processing of Visual Information. W. H. Freeman and Company (1982)Google Scholar
  16. 16.
    Mikolajczyk, K.: Detection of local features invariant to affine transformations. PhD thesis, Institut National Polytechnique de Grenoble, France (2002)Google Scholar
  17. 17.
    Schmid, C., Mohr, R., Bauckhage, C.: Evaluation of interest detectors. Int. J. Comput. Vis. 37, 151–172 (2000)zbMATHCrossRefGoogle Scholar
  18. 18.
    University of Washington: Ground truth image database (2004),

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Jonathon S. Hare
    • 1
  • Paul H. Lewis
    • 1
  1. 1.Intelligence, Agents, Multimedia Group, School of Electronics and Computer ScienceUniversity of SouthamptonSouthamptonUnited Kingdom

Personalised recommendations