Advertisement

Some Objects Are More Equal Than Others: Measuring and Predicting Importance

  • Merrielle Spain
  • Pietro Perona
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5302)

Abstract

We observe that everyday images contain dozens of objects, and that humans, in describing these images, give different priority to these objects. We argue that a goal of visual recognition is, therefore, not only to detect and classify objects but also to associate with each a level of priority which we call ‘importance’. We propose a definition of importance and show how this may be estimated reliably from data harvested from human observers. We conclude by showing that a first-order estimate of importance may be computed from a number of simple image region measurements and does not require access to image meaning.

Keywords

Human Observer Measured Importance Median Order Human Annotation Spatial Pyramid Match 
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.

References

  1. 1.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision (2004)Google Scholar
  2. 2.
    Oliva, A., Torralba, A.B.: Scene-centered description from spatial envelope properties. In: Biologically Motivated Computer Vision, pp. 263–272 (2002)Google Scholar
  3. 3.
    Weber, M., Welling, M., Perona, P.: Unsupervised learning of models for recognition. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1843, pp. 18–32. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  4. 4.
    Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: CVPR, vol. 2, pp. 264–271 (2003)Google Scholar
  5. 5.
    Sivic, J., Russell, B.C., Efros, A.A., Zisserman, A., Freeman, W.T.: Discovering objects and their localization in images. In: ICCV, 370–377 (2005)Google Scholar
  6. 6.
    Grauman, K., Darrell, T.: Efficient image matching with distributions of local invariant features. In: CVPR, vol. 2, pp. 627–634 (2005)Google Scholar
  7. 7.
    Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: CVPR, vol. 2, pp. 2169–2178 (2006)Google Scholar
  8. 8.
    Barnard, K., Forsyth, D.A.: Learning the semantics of words and pictures. In: ICCV, pp. 408–415 (2001)Google Scholar
  9. 9.
    Russell, B.C., Efros, A.A., Sivic, J., Freeman, W.T., Zisserman, A.: Using multiple segmentations to discover objects and their extent in image collections. In: Proceedings of CVPR (2006)Google Scholar
  10. 10.
    Andreetto, M., Zelnik-Manor, L., Perona, P.: Unsupervised learning of categorical segments in image collections. In: Computer Vision and Pattern Recognition (CVPR 2008) (2008)Google Scholar
  11. 11.
    Todorovic, S., Ahuja, N.: Extracting texels in 2.5d natural textures. In: Proceeddings of ICCV (2007)Google Scholar
  12. 12.
    von Ahn, L., Dabbish, L.: Labeling images with a computer game. In: CHI, pp. 319–326 (2004)Google Scholar
  13. 13.
    Russell, B.C., Torralba, A., Murphy, K.P., Freeman, W.T.: Labelme: a database and web-based tool for image annotation. Technical report (2005)Google Scholar
  14. 14.
    Elazary, L., Itti, L.: Interesting objects are visually salient. Journal of Vision 8, 1–15 (2008)CrossRefGoogle Scholar
  15. 15.
    Mayer, M., Switkes, E.: Spatial frequency taxonomy of the visual environment. Investigative Ophthalmology and Visual Science 26 (1985)Google Scholar
  16. 16.
    Shore, S.: Stephen Shore: American Surfaces. Phaidon Press (2005)Google Scholar
  17. 17.
    Shore, S., Tillman, L., Schmidt-Wulffen, S.: Uncommon Places: The Complete Works. Aperture (2005)Google Scholar
  18. 18.
  19. 19.
    Fog, A.: Calculation methods for wallenius’ noncentral hypergeometric distribution. Communications In statictics, Simulation and Computation 37, 258–273 (2008)MathSciNetCrossRefzbMATHGoogle Scholar
  20. 20.
    Manly, B.F.J.: A model for certain types of selection experiments. Biometrics 30, 281–294 (1974)CrossRefzbMATHGoogle Scholar
  21. 21.
    Kullback, S., Leibler, R.A.: On information and sufficiency. Annals of Mathematical Statistics 22, 79–86 (1951)MathSciNetCrossRefzbMATHGoogle Scholar
  22. 22.
    Angelova, A., Matthies, L., Helmick, D.M., Perona, P.: Fast terrain classification using variable-length representation for autonomous navigation. In: CVPR (2007)Google Scholar
  23. 23.
    Walther, D., Koch, C.: Modeling attention to salient proto-objects. Neural Networks 19, 1395–1407 (2006)CrossRefzbMATHGoogle Scholar
  24. 24.
    Yarbus, A.: Eye movements and vision. Plenum Press, New York (1967)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Merrielle Spain
    • 1
  • Pietro Perona
    • 1
  1. 1.California Institute of TechnologyUSA

Personalised recommendations