Abstract
This paper advocates the use of multi-coloured polygonal Markov fields for model-based image segmentation. The formal construction of consistent multi-coloured polygonal Markov fields by Arak–Clifford–Surgailis and its dynamic representation are specialised and adapted to our context. We then formulate image segmentation as a statistical estimation problem for a Gibbsian modification of an underlying polygonal Markov field, and discuss the choice of Hamiltonian. Monte Carlo techniques, including novel Gibbs updates for the Arak model, to estimate the model parameters and find an optimal partition of the image are developed. The approach is applied to image data, the first published application of polygonal Markov fields to segmentation problems in the mathematical literature.
Similar content being viewed by others
References
Arak, T. (1982). On Markovian random fields with finite number of values. In: 4th USSR-Japan symposium on probability theory and mathematical statistics, Abstracts of Communications. Tbilisi
Arak T., Surgailis D. (1989). Markov fields with polygonal realisations. Probabability Theory and Related Fields, 80, 543–579
Arak T., Surgailis D. (1991). Consistent polygonal fields. Probabability Theory and Related Fields, 89, 319–346
Arak T., Clifford P., Surgailis D. (1993). Point-based polygonal models for random graphs. Advances in Applied Probability, 25, 348–372
Baddeley A.J., van Lieshout M.N.M. (1992). ICM for object recognition. In: Dodge Y., Whittaker J. (Eds) Computational Statistics, Vol 2. Heidelberg, Physica/Springer, pp. 271–286
Borkar, V., Mitter, S. K. (1993). Stochastic processes that generate polygonal and related random fields, Research Report LIDS-P2216, MIT
Clifford P., Middleton R.D. (1989). Reconstruction of polygonal images. Journal of Applied Statistics, 16, 409–422
Clifford, P., Nicholls, G. K. (1994). A Metropolis sampler for polygonal image reconstruction, Electronic version available at: http://www.stats.ox.ac.uk/~ clifford/ papers/met_poly.html
Gimel’farb G.L. (1999). Image textures and Gibbs random fields. Dordrecht, Kluwer
Green P.J. (1995). Reversible jump Markov chain Monte Carlo computation and Bayesian model determination. Biometrika, 82, 711–732
Green P.J., Richardson S., Hjort N.L. (Eds) (2003). Highly structured stochastic systems, Oxford Statistical Science Series Vol 27. Oxford, Oxford University Press
Haario H., Saksman E. (1991). Simulated annealing process in general state space. Advances in Applied Probability, 23, 886–893
Heikkinen J., Arjas E. (1998). Non-parametric Bayesian estimation of a spatial Poisson intensity. Scandinavian Journal of Statistics, 25, 435–450
Hurn M.A., Husby O., Rue H. (2003). Advances in Bayesian image analysis. In: Green P.J., Richardson S., Hjort N.L.(Eds) Highly structured stochastic systems, Oxford Statistical Science Series Vol 27. Oxford, Oxford University Press, pp. 323–325
Liggett T. (1985). Interacting particle systems. New York, Springer
Møller J., Skare Ø. (2001). Bayesian image analysis with coloured Voronoi tessellations and a view to applications in reservoir modelling. Statistical Modelling, 1, 213–232
Møller J., Waagepetersen R.P. (1998). Markov connected component fields. Advances in Applied Probability (SGSA), 30, 1–35
Nicholls G.K. (1998). Bayesian image analysis with Markov chain Monte Carlo and coloured continuum triangulation models. Journal of the Royal Statistical Society, Series B, 60, 643–659
Ortner M. (2004). Processus ponctuels marqués pour l’extraction automatique de caricatures de bâtiments à partir de modèles numériques d’elévation. PhD Thesis, University of Nice–Sophia Antipolis.
Osher S., Paragios N. (Eds) (2003). Geometric level set methods in imaging, vision, and graphics. New York, Springer
Paskin M.A., Thrun S. (2005). Robotic mapping with polygonal random fields. In: Proceedings in Artificial Intelligence UAI-05
Rosenfeld A., Kak A.C. (1982). Digital picture processing, 2nd edn, Vol 2. Orlando, Academic Press
Schreiber, T. (2005). Random dynamics and thermodynamic limits for polygonal Markov fields in the plane. Advances in Applied Probability, 37 (4) (in press).
Tjelmeland H., Besag J. (1998). Markov random fields with higher order interactions. Scandinavian Journal of Statistics, 25, 415–433
Vincent, L. (1999). Mathematical morphology. In: O. Barndorff–Nielsen, W. S. Kendall, M. N. M. van Lieshout (Eds.) Stochastic geometry, likelihood and computation. Boca Raton: CRC Press/Chapman and Hall
Winkler G. (2003). Image analysis, random fields and Markov chain Monte Carlo methods, A mathematical introduction, 2nd edn, Applications of Mathematics, Stochastic Modelling and Applied Probability vol. 27. Berlin Heidelberg New York, Springer
Author information
Authors and Affiliations
Corresponding author
Additional information
Work carried out under project PNA4.3 ‘Stochastic Geometry’. This research was supported by the EC 6th Framework Programme Priority 2 Information Society Technology Network of Excellence MUSCLE (Multimedia Understanding through Semantics, Computation and Learning; FP6-507752), and partially by the Foundation for Polish Science (FNP) and by the Polish Minister of Scientific Research and Information Technology, grant 1 P03A 018 28 (2005-2007) [the third author].
About this article
Cite this article
Kluszczyński, R., van Lieshout, M.N.M. & Schreiber, T. Image segmentation by polygonal Markov Fields. AISM 59, 465–486 (2007). https://doi.org/10.1007/s10463-006-0062-8
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10463-006-0062-8