Dynamic Visual Search Using Inner-Scene Similarity: Algorithms and Inherent Limitations

  • Tamar Avraham
  • Michael Lindenbaum
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3022)


A dynamic visual search framework based mainly on inner-scene similarity is proposed. Algorithms as well as measures quantifying the difficulty of search tasks are suggested. Given a number of candidates (e.g. sub-images), our basic hypothesis is that more visually similar candidates are more likely to have the same identity. Both deterministic and stochastic approaches, relying on this hypothesis, are used to quantify this intuition. Under the deterministic approach, we suggest a measure similar to Kolmogorov’s ε-covering that quantifies the difficulty of a search task and bounds the performance of all search algorithms. We also suggest a simple algorithm that meets this bound. Under the stochastic approach, we model the identities of the candidates as correlated random variables and characterize the task using its second order statistics. We derive a search procedure based on minimum MSE linear estimation. Simple extensions enable the algorithm to use top-down and/or bottom-up information, when available.


Feature Vector Visual Search Search Task Stochastic Approach Partial Description 
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.
    Avraham, T., Lindenbaum, M.: A Probabilistic Estimation Approach for Dynamic Visual Search. In: Proceedings of International Workshop on Attention and Performance in Computer Vision (WAPCV), pp. 1–8 (2003)Google Scholar
  2. 2.
    Avraham, T., Lindenbaum, M.: CIS Report #CIS-2003-02. Technion - Israel Institute of Technology, Haifa 32000, Israel (2003)Google Scholar
  3. 3.
    Duncan, J., Humphreys, G.W.: Visual search and stimulus similarity. Psychological Review 96, 433–458 (1989)CrossRefGoogle Scholar
  4. 4.
    Gonzalez, T.F.: Clustering to minimize the maximum intercluster distance. Theoretical Computer Science 38(2-3), 293–306 (1985)zbMATHCrossRefMathSciNetGoogle Scholar
  5. 5.
    Humphreys, G.W., Muller, H.J.: Search via recursive rejection (serr): A connectionist model of visual search. Cognitive Psychology 25, 43–110 (1993)CrossRefGoogle Scholar
  6. 6.
    Itti, L.: Models of bottom-up and top-down visual attention. Thesis (January 2000)Google Scholar
  7. 7.
    Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. PAMI 20(11), 1254–1259 (1998)Google Scholar
  8. 8.
    Koch, C., Ullman, S.: Shifts in selective visual attention: towards the underlying neural vircuity. Human Neurobiology 4, 219–227 (1985)Google Scholar
  9. 9.
    Kolmogorov, A.N., Tikhomirov, V.M.: Epsilon-entropy and epsilon-capacity of sets in functional spaces. AMS Translations. Series 2 17, 277–364 (1961)Google Scholar
  10. 10.
    Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proc. 8th ICCV, July 2001, vol. 2, pp. 416–423 (2001)Google Scholar
  11. 11.
    Neisser, U.: Cognitive Psychology. Appleton-Century-Crofts, New York (1967)Google Scholar
  12. 12.
    Nene, S., Nayar, S., Murase, H.: Columbia object image library (coil-100). Technical Report CUCS-006-96, Department of Computer Science, Columbia University (February 1996)Google Scholar
  13. 13.
    Papoulis, A., Pillai, S.U.: Probability, Random Variables, and Stochastic Processes, 4th edn. McGraw-Hill, New York (2002)Google Scholar
  14. 14.
    Rao, R.P.N., Ballard, D.H.: An active vision architecture based on iconic representations. Artificial Intelligence 78(1-2), 461–505 (1995)CrossRefGoogle Scholar
  15. 15.
    Rimey, R.D., Brown, C.M.: Control of selective perception using bayes nets and decision theory. International Journal of Computer Vision 12, 173–207 (1994)CrossRefGoogle Scholar
  16. 16.
    Swain, M.J., Ballard, D.H.: Color indexing. IJCV 7, 11–32 (1991)CrossRefGoogle Scholar
  17. 17.
    Tagare, H., Toyama, K., Wang, J.G.: A maximum-likelihood strategy for directing attention during visual search. IEEE PAMI 23(5), 490–500 (2001)Google Scholar
  18. 18.
    Torralba, A., Sinha, P.: Statistical context priming for object detection. In: Proceedings of the 8th ICCV, pp. 763–770 (2001)Google Scholar
  19. 19.
    Treisman, A., Gelade, G.: A feature integration theory of attention. Cognitive Psychology 12, 97–136 (1980)CrossRefGoogle Scholar
  20. 20.
    Tsotsos, J.K.: On the relative complexity of active versus passive visual search. IJCV 7(2), 127–141 (1992)CrossRefGoogle Scholar
  21. 21.
    Tsotsos, J.K., Culhane, S.M., Wai, W.Y.K., Lai, Y., Davis, N., Nuflo, F.J.: Modeling visual attention via selective tuning. Artificial intelligence 78(1-2), 507–545 (1995)CrossRefGoogle Scholar
  22. 22.
    Wixson, L.E., Ballard, D.H.: Using intermediate objects to improve the efficiency of visual-search. IJCV 12(2-3), 209–230 (1994)CrossRefGoogle Scholar
  23. 23.
    Wolfe, J.M.: Guided search 2.0: A revised model of visual search. Psychonomic. Bulletin and Review 1(2), 202–238 (1994)Google Scholar
  24. 24.
    Yarbus, A.L.: Eye Movements and Vision. Plenum Press, New York (1967)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Tamar Avraham
    • 1
  • Michael Lindenbaum
    • 1
  1. 1.Computer Science DepartmentTechnionHaifaIsrael

Personalised recommendations