Abstract
Texture is an important characteristic of the appearance of objects in natural scenes and is a crucial cue in visual perception. It plays an important role in computer vision, graphics, and image encoding. Understanding texture is an essential part of understanding human vision.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
We assume the histogram of each sub-band I(α) is normalized such that \(\sum _i H_i^{(\alpha )} =1\), and therefore all the \(\{\lambda _i^{(\alpha )}, i=1, \ldots , L\}\) computed in this algorithm have one extra degree of freedom for each α, i.e., we can increase \(\{\lambda _i^{(\alpha )}, i=1, \ldots , L\}\) by a constant without changing p(I; ΛK, SK). This constant will be absorbed by the partition function Z( ΛK).
- 2.
We assume D →Z2 in the sense of van Hove, i.e., the ratio between the boundary and the size of D goes to 0.
- 3.
We hope that the notation h(I) = h will not confuse the reader. The h on the left is a function of I for extracting statistics, while the h on the right is a specific value of the statistics.
- 4.
In the i.i.d. case, \(q({\mathbf {I}}_{{D}_0}; h)\) is both the marginal distribution and the conditional distribution of q(I; h), while in random fields, we only consider the conditional distribution.
References
Barbu, A. & Zhu, S.-C. (2005). Incorporating visual knowledge representation in stereo reconstruction. In Tenth IEEE International Conference on Computer Vision (ICCV’05) Volume 1 (Vol. 1, pp. 572–579).
Behrmann, J., Grathwohl, W., Chen, R. T., Duvenaud, D., & Jacobsen, J.-H. (2018). Invertible residual networks. ar**v preprint ar**v:1811.00995.
Bergen, J. R., & Adelson, E. (1991). Theories of visual texture perception. Spatial Vision, 10, 114–134.
Besag, J. (1974). Spatial interaction and the statistical analysis of lattice systems. Journal of the Royal Statistical Society: Series B (Methodological), 36(2), 192–225.
Breiman, L., Friedman, J., Stone, C. J., & Olshen, R. A. (1984). Classification and regression trees.
Chandler, D. (1987). Introduction to modern statistical mechanics. In D. Chandler (Ed.) Introduction to Modern Statistical Mechanics (pp. 288). Foreword by D. Chandler. Oxford University Press. ISBN-10: 0195042778. ISBN-13: 9780195042771, 1.
Cross, G. R., & Jain, A. K. (1983). Markov random field texture models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1, 25–39.
Daugman, J. G. (1985). Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. JOSA A, 2(7), 1160–1169.
De Bonet, J., & Viola, P. (1997). A non-parametric multi-scale statistical model for natural images. Advances in Neural Information Processing Systems, 10.
Diaconis, P., & Freedman, D. (1981). On the statistics of vision: the julesz conjecture. Journal of Mathematical Psychology, 24(2), 112–138.
Geman, S., & Geman, D. (1997). Stochastic relaxation, gibbs distributions, and the bayesian restoration of images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 6(4), 380–393.
Gibbs, J. W. (1902). Elementary principles in statistical mechanics: Developed with especial reference to the rational foundations of thermodynamics. C. Scribner’s sons.
Griffiths, R. B., & Ruelle, D. (1971). Strict convexity (“continuity”) of the pressure in lattice systems. Communications in Mathematical Physics, 23(3), 169–175
Grindrod, P. (1996). The theory and applications of reaction-diffusion equations: patterns and waves. Clarendon Press.
Julesz, B. (1962). Visual pattern discrimination. IRE Transactions on Information Theory, 8(2), 84–92.
Landau, L. D., & Lifshitz, E. M. (1959). Statistical physics, 5, 482.
Lanford, O. E. (1973). Statistical mechanics and mathematical problems. In Entropy and equilibrium states in classical statistical mechanics (pp. 1–113).
Murray, J. D. (1981). A pre-pattern formation mechanism for animal coat markings. Journal of Theoretical Biology, 88(1), 161–199.
Nitzberg, M., & Shiota, T. (1992). Nonlinear image filtering with edge and corner enhancement. IEEE Transactions on Pattern Analysis & Machine Intelligence, 14(8), 826–833.
Perona, P., & Malik, J. (1990). Scale-space and edge detection using anisotropic diffusion. IEEE Transactions on Pattern Analysis and Machine Intelligence, 12(7), 629–639.
Turing, A. M. (1990). The chemical basis of morphogenesis. Bulletin of Mathematical Biology, 52(1–2), 153–197.
Wu, Y. N., Zhu, S.-C., & Liu, X. (1999b). Equivalence of julesz and gibbs texture ensembles. In Proceedings of the Seventh IEEE International Conference on Computer Vision (Vol. 2, pp. 1025–1032). IEEE.
Wu, Y. N., Zhu, S. C., & Liu, X. (2000). Equivalence of julesz ensembles and frame models. International Journal of Computer Vision, 38(3), 247–265.
Zhu, S.-C., & Mumford, D. (1998). Grade: Gibbs reaction and diffusion equations. In Sixth International Conference on Computer Vision (ICCV) (pp. 847–854). IEEE.
Zhu, S.-C., Wu, Y. N., & Mumford, D. (1998). Filters, random fields and maximum entropy (frame): Toward a unified theory for texture modeling. International Journal of Computer Vision, 27(2), 107–126.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2023 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Zhu, SC., Wu, Y.N. (2023). Textures. In: Computer Vision. Springer, Cham. https://doi.org/10.1007/978-3-030-96530-3_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-96530-3_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-96529-7
Online ISBN: 978-3-030-96530-3
eBook Packages: Computer ScienceComputer Science (R0)