Advertisement

Significantly Different Textures: A Computational Model of Pre-attentive Texture Segmentation

  • Ruth Rosenholtz
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1843)

Abstract

Recent human vision research [1] suggests modelling preattentive texture segmentation by taking a set of feature samples from a local region on each side of a hypothesized edge, and then performing standard statistical tests to determine if the two samples differ significantly in their mean or variance. If the difference is significant at a specified level of confidence, a human observer will tend to pre-attentively see a texture edge at that location. I present an algorithm based upon these results, with a well specified decision stage and intuitive, easily fit parameters. Previous models of pre-attentive texture segmentation have poorly specified decision stages, more unknown free parameters, and in some cases incorrectly model human performance. The algorithm uses heuristics for guessing the orientation of a texture edge at a given location, thus improving computational efficiency by performing the statistical tests at only one orientation for each spatial location.

Keywords

Decision Stage Internal Noise Resultant Vector Texture Segmentation Orientation Estimate 
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.
    R. Rosenholtz. What statistics determine segmentation of orientation-defined textures? Perception (Suppl.), 26:111, 1997.Google Scholar
  2. 2.
    B. Julesz. Experiments in the visual perception of texture. Sci. Amer., 232:34–43, 1975.CrossRefGoogle Scholar
  3. 3.
    B. Julesz. Texton gradients: the texton theory revisited. Biol. Cybern., 54:245–51, 1986.zbMATHCrossRefGoogle Scholar
  4. 4.
    J. Beck, K. Prazdny, & A. Rosenfeld. A theory of textural segmentation. In Human & Machine Vision, Beck, Hope, & Rosenfeld, eds. (New York: Academic Press), 1983.Google Scholar
  5. 5.
    M. R. Turner. Texture discrimination by Gabor functions. Biol. Cybern., 55:71–82, 1986.Google Scholar
  6. 6.
    J. Bergen & E. Adelson. Early vision and texture perception. Nature, 333:363–4, 1988.CrossRefGoogle Scholar
  7. 7.
    J. Malik & P. Perona. Preattentive texture discrimination with early vision mechanisms. J. Opt. Soc. Am.. A., 7(5):923–32, 1990.Google Scholar
  8. 8.
    J. R. Bergen & M. S. Landy. Computational modeling of visual texture segregation. In Computational models of visual perception, Landy & Movshon, eds. (Cambridge, MA: MIT Press), 1991.Google Scholar
  9. 9.
    F. A. A. Kingdom & D. R. T. Keeble. On the mechanism for scale invariance in orientation-defined textures. Vision Research, 39:1477–89, 1999.CrossRefGoogle Scholar
  10. 10.
    E. Batschelet. Circular statistics in biology. (London: Academic Press), 1981.zbMATHGoogle Scholar
  11. 11.
    H. C. Nothdurft. Sensitivity for structure gradient in texture discrimination tasks. Vision Research, 25:1957–68, 1985.CrossRefGoogle Scholar
  12. 12.
    B. A. Dosher & Z.-L. Lu. Mechanisms of perceptual learning. Investigative Ophthalmology & Visual Science (Suppl.), 39(4):912, 1998.Google Scholar
  13. 13.
    R. Duda & P. Hart. Pattern classification and scene analysis. (New York: Wiley), 1973.zbMATHGoogle Scholar
  14. 14.
    J. Puzicha, T. Hoffman, J. Buhmann. Non-parametric similarity measures for unsupervised texture segmentation and image retrieval. Proc. CVPR, pp. 267–72, Puerto Rico, June, 1997.Google Scholar
  15. 15.
    J. Shi & J. Malik. Self-inducing relational distance and its application to image segmentation. Proc. ECCV, pp. 528–43, Freiburg, Germany, June, 1998.Google Scholar
  16. 16.
    M. A. Ruzon & C. Tomasi. Color edge detection with the compass operator. Proc. CVPR, pp. 160–6, Fort Collins, CO, June, 1999.Google Scholar
  17. 17.
    H. Voorhees & T. Poggio. Computing texture boundaries from images. Nature, 333:364–7, 1988.CrossRefGoogle Scholar
  18. 18.
    J. H. Elder & S. W. Zucker. Local scale control for edge detection and blue estimation. Proc. ECCV, pp. 57–69, 1996.Google Scholar
  19. 19.
    D. H. Marimont & Y. Rubner. A probabilistic framework for edge detection and scale selection. Proc. ICCV, pp. 207–14, Bombay, India, January, 1998.Google Scholar
  20. 20.
    M. N. Fesharki & G. R. Hellestrand. A new edge detection algorithm based on a statistical approach. Proc. ISSIPNN, 1:21–4, 1994.Google Scholar
  21. 21.
    J. Weber & J. Malik. Scene partitioning via statistic-based region growing. Tech. report UCB/CSD-94-817, Comp. Sci. Div. (EECS), Univ. of California, Berkeley, 1994.Google Scholar
  22. 22.
    E. Barth, C. Zetzsche, F. Giulianini, & I. Rentschler. Intrinsic 2D features as textons. J. Opt. Soc. Am. A., 15(7): 1723–32, 1998.CrossRefGoogle Scholar
  23. 23.
    W. T. Freeman & E. H. Adelson. The design and use of steerable filters. IEEE PAMI, 13(9):891–906, 1995.Google Scholar
  24. 24.
    R. M. Haralick. Digital step edges from zero crossings of the 2nd directional derivative. IEEE PAMI, 6(1):58–68, 1984.Google Scholar
  25. 25.
    R. Gurnsey & R. Browse. Micropattern properties and presentation conditions influencing visual texture discrimination. Percept. Psychophys., 41:239–52, 1987.Google Scholar
  26. 26.
    B. Krose. Local structure analyzers as determinants of preattentive pattern discrimination. Biol. Cybern., 55:289–98, 1987.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Ruth Rosenholtz
    • 1
  1. 1.Xerox PARCPalo Alto

Personalised recommendations