We initiate a study of property testing as applied to visual properties of images. Property testing is a rapidly developing area investigating algorithms that, with a small number of local checks, distinguish objects satisfying a given property from objects which need to be modified significantly to satisfy the property. We study visual properties of discretized images represented by n× n matrices of binary pixel values. We obtain algorithms with query complexity independent of n for several basic properties: being a half-plane, connectedness and convexity.


Query Complexity Property Testing Visual Property Black Pixel White Pixel 
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.
    Batu, T., Ergun, F., Kilian, J., Magen, A., Raskhodnikova, S., Rubinfeld, R., Sami, R.: A Sublinear Algorithm for Weakly Approximating Edit Distance. In: Proceedings of the 35th ACM STOC (2003)Google Scholar
  2. 2.
    Ben-Sasson, E., Harsha, P., Raskhodnikova, S.: 3CNF Properties are Hard to Test. In: Proceedings of the 35th ACM STOC (2003)Google Scholar
  3. 3.
    Blumer, A., Ehrenfeucht, A., Haussler, D., Warmuth, M.: Learnability and the Vapnik-Chervonenkis dimension. Journal of the Association for computing machinery 36(4), 929–965 (1989)MATHMathSciNetGoogle Scholar
  4. 4.
    Bogdanov, A., Obata, K., Trevisan, L.: A linear lower bound on the query complexity of property testing algorithms for 3-coloring in bounded-degree graphs. In: Proceedings of the 42nd IEEE FOCS (2002)Google Scholar
  5. 5.
    Chazelle, B., Rubinfeld, R., Trevisan, L.: Approximating the minimum spanning tree weight in sublinear time. In: Orejas, F., Spirakis, P.G., van Leeuwen, J. (eds.) ICALP 2001. LNCS, vol. 2076, p. 190. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  6. 6.
    Czumaj, A., Sohler, C.: Property testing with geometric queries. In: Proceedings of the 9th European Symposium on Algorithms, pp. 266–277 (2001)Google Scholar
  7. 7.
    Czumaj, A., Sohler, C., Ziegler, M.: Property testing in computational geometry. In: Proceedings of the 8th European Symposium on Algorithms, pp. 155–166 (2000)Google Scholar
  8. 8.
    Ehrenfeucht, A., Haussler, D., Kearns, M., Valiant, L.: General Lower Bound on the Number of Examples Needed for Learning. Information and Computation 82(3), 247–261 (1989)MATHCrossRefMathSciNetGoogle Scholar
  9. 9.
    Fischer, E.: The art of uninformed decisions: A primer to property testing. The Computational Complexity Column of The Bulletin of the European Association for Theoretical Computer Science 75, 97–126 (2001)MATHGoogle Scholar
  10. 10.
    Fischer, E., Newman, I.: Testing of matrix properties. In: Proceedings of the 33rd ACM STOC, pp. 286-295 (2001)Google Scholar
  11. 11.
    Goldreich, O., Goldwasser, S., Ron, D.: Property testing and its connection to learning and approximation. Journal of the ACM 45, 653–750 (1998)MATHCrossRefMathSciNetGoogle Scholar
  12. 12.
    Goldreich, O., Ron, D.: Property Testing in Bounded Degree Graphs. In: Proceedings of the 28th ACM STOC (1997)Google Scholar
  13. 13.
    Kushilevitz, E., Roth, D.: On Learning Visual Concepts and DNF Formulae. Machine Learning (1996)Google Scholar
  14. 14.
    Maass, W., Turan, G.: On the complexity of learning from counterexamples. In: Proceedings of the 30th IEEE FOCS, pp. 262–267 (1989)Google Scholar
  15. 15.
    Ron, D.: Property testing (a tutorial). In: Rajasekaran, S., Pardalos, P.M., Reif, J.H., Rolimeds, J.D.P. (eds.) Handbook of Randomized Computing, Kluwer Press, Dordrecht (2001)Google Scholar
  16. 16.
    Rubinfeld, R., Sudan, M.: Robust characterization of polynomials with applications to program testing. SIAM Journal of Computing 25, 252–271 (1996)MATHCrossRefMathSciNetGoogle Scholar
  17. 17.
    Valiant, L.: A theory of the learnable. Communications of the ACM 27, 1134–1142 (1984)MATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Sofya Raskhodnikova
    • 1
  1. 1.MIT Laboratory for Computer ScienceCambridgeUSA

Personalised recommendations