Skip to main content
SpringerLink
Log in

Natural Image Statistics for Natural Image Segmentation

  • Published:
International Journal of Computer Vision Aims and scope Submit manuscript

Abstract

We integrate a model for filter response statistics of natural images into a variational framework for image segmentation. Incorporated in a sound probabilistic distance measure, the model drives level sets toward meaningful segmentations of complex textures and natural scenes. Despite its enhanced descriptive power, our approach preserves the efficiency of level set based segmentation since each region comprises two model parameters only. Analyzing thousands of natural images we select suitable filter banks, validate the statistical basis of our model, and demonstrate that it outperforms variational segmentation methods using second-order statistics.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Belongie, S., Carson, C., Greenspan, H., and Malik, J. 1998. Color- and texture-based image segmentation using EM and its application to content-based image retrieval. In Proc. of the ICCV.

  • Brodatz, P. 1966. Textures: A Photographic Album for Artists and Designers. Dover Publications: New York.

    Google Scholar 

  • Buccigrossi, R.W. and Simoncelli, E.P. 1999. Image compression via joint statistical characterization in the wavelet domain. IEEE Trans. on Image Proc., 8(12):1688–1700.

    Google Scholar 

  • Caselles, V., Kimmel, R., and Sapiro. G. 1997. Geodesic active contours. Int. J. of Comp. Vision, 22(1):61–79.

    Google Scholar 

  • Chan, T.F. and Vese, L.A. 2001. Active contours without edges. IEEE Trans. on Image Proc., 10(2):266–277.

    Google Scholar 

  • Cremers, D., Sochen, N., and Schnörr, C. 2004. Dynamic labeling for variational recognition-driven image segmentation. In Proc. of the ECCV (to appear).

  • Fowlkes, C., Belongie, S., Chung, F., and Malik, J. 2004. Spectral grouping usingthe Nyström method. IEEE Trans. Patt. Anal. Mach. Intell., 26(3):214–225.

    Google Scholar 

  • Freeman, W.T. and Adelson, E.H. 1991. The design and use of steerable filters. IEEE Trans. Patt. Anal. Mach. Intell., 13(9):891–906.

    Google Scholar 

  • Geusebroek, J.M. and Smeulders, A.W.M. 2003. Fragmentation in the vision of scenes. In Proc. of the ICCV, vol. 1, pp. 130–135.

    Google Scholar 

  • GMBV. 2002. First international workshop on generative-model-based vision (GMBV2002), in conjunction with ECCV 2002. http://www.diku.dk/publikationer/tekniske. rapporter/2002/02-01/, Copenhagen, Denmark.

  • Hansen, M.H. and Yu, B. 2001. Model selection and the principle of minimum description length. J. of the Americ. Stat. Assoc., 96(454):746–774.

    Google Scholar 

  • Heeger, D.J. and Bergen, J.R. 1995. Pyramid-based texture analysis/synthesis. In Proc. of SIGGRAPH, pp. 229–238.

  • Huang, J. and Mumford, D. 1999. Statistics of natural images and models. In Proc. of the ICCV, vol. 1, pp. 541–547.

    Google Scholar 

  • Jehan-Besson, S., Barlaud, M., and Aubert, G. 2003. DREAM2S: Deformable regions driven by an Eulerian accurate minimization method for image and video segmentations. Int. J. of Comp. Vision, 53(1):45–70.

    Google Scholar 

  • Joshi, R.L., Crump, V.J., and Fischer, T.R. 1995. Image subband coding using arithmetic coded trellis coded quantization. IEEE Trans. on Circuits and Systems for Video Technology, 5(6):515–523.

    Google Scholar 

  • Keuchel, J., Schnörr, C., Schellewald, C., and Cremers, D. 2003. Binary partitioning, perceptual grouping, and restoration with semidefinite programming. IEEE Trans. Patt. Anal. Mach. Intell., 25(11):1364–1379.

    Google Scholar 

  • Kichenassamy, S., Kumar, A., Olver, P.J., Tannenbaum, A., and Yezzi, A.J. 1995. Gradient flows and geometric active contour models. In Proc. of the ICCV, pp. 810–815.

  • Leclerc, Y.G. 1989. Constructing simple stable descriptions for image partitioning. Int. J. of Comp. Vision, 3(1):73–102.

    Google Scholar 

  • Liu, X. and Wang, D. 2000. Texture classification using spectral histograms. Technical report, Dept. of Comp. and Inform. Science, Ohio State University, Columbus, OH, USA.

    Google Scholar 

  • LoPresto, S.M. and Ramchandran, K. 1997. Image coding based on mixture modeling of wavelet coefficients and a fast estimation-quantization framework. In Proc. of the Data Compr. Conf. (DCC), pp. 221–230.

  • Mallat, S.G. 1998. A theory of multiresolution signal decomposition: The wavelet representation. IEEE Trans. Patt. Anal. Mach. Intell., 11(7):674–693.

    Google Scholar 

  • Martin, D., Fowlkes, C., Tal, D., and Malik, J. 2001. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In Proc. of the ICCV, vol. 2, pp. 416–423.

    Google Scholar 

  • Mumford, D. 1994. Bayesian rationale for the variational formulation. In Geometry-Driven Diffusion in Computer Vision, B. ter Haar Romeny (Ed.), Kluwer Acad. Publ.: Dordrecht, pp. 135–146.

    Google Scholar 

  • Mumford, D. and Shah, J. 1989. Optimal approximations by piecewise smooth functions and associated variational problems. Comm. Pure Appl. Math.,42:577–685.

    MathSciNet  MATH  Google Scholar 

  • Paragios, N. and Deriche, R. 2002. Geodesic active regions and level set methods for supervised texture segmentation. Int. J. of Comp. Vision, 46(3):223–247.

    Google Scholar 

  • Picard, R., Graczyk, C., Mann, S., Wachman, J., Picard, L., and Campbell, L. 1995. VisTex vision texture database. MIT Media Lab.

  • Portilla, J. and Simoncelli, E.P. 2000. A parametric texture model based on joint statistics of complex wavelet coefficients. Int. J. of Comp. Vision, 40(1):49–71.

    Google Scholar 

  • Puzicha, J., Hofmann, T., and Buhmann, J.M. 1999. Histogram clustering for unsupervised segmentation and image retrieval. Pattern Recog. Letters, 20:899–909.

    Google Scholar 

  • Puzicha, J., Rubner, Y., Tomasi, C., and Buhmann, J.M. 1999. Empirical evaluation of dissimilarity measures for color and texture. In Proc. of the ICCV, vol. 2, pp. 1165–1172.

    Google Scholar 

  • Randen, T. and Husøy, J.H. 1999. Filtering for texture classification: A comparative study. IEEE Trans. Patt. Anal. Mach. Intell., 21(4):291–310.

    Google Scholar 

  • Reininger, R.C. and Gibson, J.D. 1983. Distributions of the two-dimensional DCT coefficients for images. IEEE Trans. on Communications, 31(6):835–839.

    Google Scholar 

  • Rissanen, J. 1978. Modelling by the shortest data description. Automatica, 14:465–471.

    Article  Google Scholar 

  • Rousson, M., Brox, T., and Deriche, R. 2003. Active unsupervised texture segmentation on a diffusion based feature space. In Proc. of the IEEE Conf. on Comp. Vis. a. Patt. Recog., vol. 2, pp. 699–704.

    Google Scholar 

  • Rubner, Y., Tomasi, C., and Guibas, L.J. 2000. The earth movers distance as a metric for image retrieval. Int. J. of Comp. Vision, 40(2):99–121.

    Google Scholar 

  • Shi, J. and Malik, J. 2000. Normalized cuts and image segmentation. IEEE Trans. Patt. Anal. Mach. Intell., 22(8):888–905.

    Google Scholar 

  • Simon, J. 1980. Differentiation with respect to the domain in boundary value problems. Numerical Functional Analysis and Optimization, 2(7):649–687.

    Google Scholar 

  • Simoncelli, E.P. and Adelson, E.H. 1996. Noise removal via Bayesian wavelet coring. In Third Int’l Conf on Image Proc, Lausanne, IEEE Sig. Proc. Soc, pp. 379–382.

  • Simoncelli, E.P. and Freeman, W.T. 1995. The steerable pyramid: A flexible architecture for multi-scale derivative computation. In Second Int’l Conf. on Image Proc., Washington, DC.

  • Sokolowski, J. and Zolesio, J.-P. 1991. Introduction to Shape Optimization. Springer: New York.

    Google Scholar 

  • Srivastava, A., Liu, X., and Grenander, U. 2002. Universal analytical forms for modeling image probabilities. IEEE Trans. Patt. Anal. Mach. Intell., 24(9):1200–1214.

    Google Scholar 

  • Tang, M. and Ma, S. 2001. General scheme of region competition based on scale space. IEEE Trans. Patt. Anal. Mach. Intell., 23(12):1366–1378.

    Google Scholar 

  • Tu, Z. and Zhu, S.C. 2002. Image segmentation by data-driven Markov Chain Monte Carlo. IEEE Trans. Patt. Anal. Mach. Intell., 24(5):657–673.

    Google Scholar 

  • van Hateren, J.H. and van der Schaaf, A. 1998. Independent component filtering of natural images compared with simple cells in primary visual cortex. In Proc. of the Royal Soc., London, pp. 359–366.

  • Vese, L.A. and Chan, T.F. 2002. A multiphase level set framework for image segmentation using the mumford and shah model. Int. J. of Comp. Vision, 50(3):271–293.

    Google Scholar 

  • Wainwright, M.J., Simoncelli, E.P., and Willsky, A.S. 2001. Random cascades on wavelet trees and their use in analyzing and modeling natural images. Applied and Computational Harmonic Analysis, 11(1):89–123.

    Google Scholar 

  • Wallace, C.S. and Boulton, D.M. 1968. An information measure for classification. Comp. J., 11(2):185–194.

    Google Scholar 

  • Wu, Y., Chan, K.L., and Huang, Y. 2003. Image texture classification based on finite gaussian mixture models. In 3rd Int. Workshop on Text. Anal. and Synth., ICCV, M. Chantler (Ed.), pp. 107–112.

  • Wu, Y., Zhu, S.C., and Liu, X. 2000. Equivalence of Julesz ensembles and FRAME models. Int. J. of Comp. Vision, 38(3):247–265.

    Google Scholar 

  • Zhu, S.C., Liu, X., and Wu, Y.N. 2000. Exploring texture ensembles by efficient Markov Chain Monte Carlo-toward a ‘trichromacy’ theory of texture. IEEE Trans. Patt. Anal. Mach. Intell., 22(6):554–569.

    Google Scholar 

  • Zhu, S.C. and Mumford, D. 1997. Prior learning and Gibbs reaction–diffusion. IEEE Trans. Patt. Anal. Mach. Intell., 19(11):1236–1250.

    Google Scholar 

  • Zhu, S.C., Wu, Y., and Mumford, D. 1998. Filters, random fields and maximum entropy (FRAME). Int. J. of Comp. Vision, 27(2):1–20.

    Google Scholar 

  • Zhu, S.C. and Yuille, A.L. 1996. Region competition: Unifying snakes, region growing, and Bayes/MDL for multiband image segmentation. IEEE Trans. Patt. Anal. Mach. Intell., 18(9):884–900.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Computer Vision, Graphics, and Pattern Recognition Group, Department of Mathematics and Computer Science, University of Mannheim, D-68131, Mannheim, Germany

    Matthias Heiler & Christoph Schnörr

Authors
  1. Matthias Heiler
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Christoph Schnörr
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Matthias Heiler.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Heiler, M., Schnörr, C. Natural Image Statistics for Natural Image Segmentation. Int J Comput Vision 63, 5–19 (2005). https://doi.org/10.1007/s11263-005-4944-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11263-005-4944-7

Keywords

Search

Navigation