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.
Chapter PDF
References
R. Rosenholtz. What statistics determine segmentation of orientation-defined textures? Perception (Suppl.), 26:111, 1997.
B. Julesz. Experiments in the visual perception of texture. Sci. Amer., 232:34–43, 1975.
B. Julesz. Texton gradients: the texton theory revisited. Biol. Cybern., 54:245–51, 1986.
J. Beck, K. Prazdny, & A. Rosenfeld. A theory of textural segmentation. In Human & Machine Vision, Beck, Hope, & Rosenfeld, eds. (New York: Academic Press), 1983.
M. R. Turner. Texture discrimination by Gabor functions. Biol. Cybern., 55:71–82, 1986.
J. Bergen & E. Adelson. Early vision and texture perception. Nature, 333:363–4, 1988.
J. Malik & P. Perona. Preattentive texture discrimination with early vision mechanisms. J. Opt. Soc. Am.. A., 7(5):923–32, 1990.
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.
F. A. A. Kingdom & D. R. T. Keeble. On the mechanism for scale invariance in orientation-defined textures. Vision Research, 39:1477–89, 1999.
E. Batschelet. Circular statistics in biology. (London: Academic Press), 1981.
H. C. Nothdurft. Sensitivity for structure gradient in texture discrimination tasks. Vision Research, 25:1957–68, 1985.
B. A. Dosher & Z.-L. Lu. Mechanisms of perceptual learning. Investigative Ophthalmology & Visual Science (Suppl.), 39(4):912, 1998.
R. Duda & P. Hart. Pattern classification and scene analysis. (New York: Wiley), 1973.
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.
J. Shi & J. Malik. Self-inducing relational distance and its application to image segmentation. Proc. ECCV, pp. 528–43, Freiburg, Germany, June, 1998.
M. A. Ruzon & C. Tomasi. Color edge detection with the compass operator. Proc. CVPR, pp. 160–6, Fort Collins, CO, June, 1999.
H. Voorhees & T. Poggio. Computing texture boundaries from images. Nature, 333:364–7, 1988.
J. H. Elder & S. W. Zucker. Local scale control for edge detection and blue estimation. Proc. ECCV, pp. 57–69, 1996.
D. H. Marimont & Y. Rubner. A probabilistic framework for edge detection and scale selection. Proc. ICCV, pp. 207–14, Bombay, India, January, 1998.
M. N. Fesharki & G. R. Hellestrand. A new edge detection algorithm based on a statistical approach. Proc. ISSIPNN, 1:21–4, 1994.
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.
E. Barth, C. Zetzsche, F. Giulianini, & I. Rentschler. Intrinsic 2D features as textons. J. Opt. Soc. Am. A., 15(7): 1723–32, 1998.
W. T. Freeman & E. H. Adelson. The design and use of steerable filters. IEEE PAMI, 13(9):891–906, 1995.
R. M. Haralick. Digital step edges from zero crossings of the 2nd directional derivative. IEEE PAMI, 6(1):58–68, 1984.
R. Gurnsey & R. Browse. Micropattern properties and presentation conditions influencing visual texture discrimination. Percept. Psychophys., 41:239–52, 1987.
B. Krose. Local structure analyzers as determinants of preattentive pattern discrimination. Biol. Cybern., 55:289–98, 1987.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Rosenholtz, R. (2000). Significantly Different Textures: A Computational Model of Pre-attentive Texture Segmentation. In: Vernon, D. (eds) Computer Vision — ECCV 2000. ECCV 2000. Lecture Notes in Computer Science, vol 1843. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45053-X_13
Download citation
DOI: https://doi.org/10.1007/3-540-45053-X_13
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-67686-7
Online ISBN: 978-3-540-45053-5
eBook Packages: Springer Book Archive