Abstract
From remote sensing of the environment, to brain scans in medicine, the growth in the use of image data has motivated a parallel increase in statistical techniques for analysing these images. A particular area of growth has been in Bayesian models and corresponding computational methods. Bayesian approaches have been proposed to address the gamut of supervised and unsupervised inferential aims in image analysis. In this article we provide a general review of these approaches, with a focus on unsupervised analysis of 2-D images. Four exemplar methods that canvas the broad aims of image modelling and analysis are described. An exposition of these approaches is provided by applying them to an environmental case study involving the use of satellite data to assess water quality in the Great Barrier Reef, Australia. The techniques considered in detail are hidden Markov random fields (MRF), Gaussian MRF, Poisson/gamma random fields, and Voronoi tessellations. We also consider a variety of enabling computational algorithms, including MCMC, variational Bayes and integrated nested Laplace approximations. We compare the different aims and inferential capabilities of the models and discuss the advantages and drawbacks of the corresponding computational algorithms.
Similar content being viewed by others
References
Alston C, Mengersen K (2010) Allowing for the effect of data binning in a Bayesian normal mixture model. Comput Stat Data Anal 54(4):916–923
Alston CL, Mengersen KL, Thompson JM, Littlefield PJ, Perry D, Ball AJ (2005) Extending the Bayesian mixture model to incorporate spatial information in analysing sheep CAT scan images. Aust J Agric Res 56(4):373–388
Antoniak C (1974) Mixtures of Dirichlet processes with applications to Bayesian nonparametric problems. Ann Stat 2(6):1152–1174
Banerjee S, Carlin B, Gelfand A (2004) Hierarchical modeling and analysis for spatial data. Chapman & Hall/CRC Press, Boca Raton
Beal MJ, Ghahramani Z (2003) The variational Bayesian EM algorithm for incomplete data: with application to scoring graphical model structures. In: Proceedings of the seventh Valencia international meeting, volume 7 of Bayesian statistics. Oxford University Press, London, pp 453–464
Besag J (1974) Spatial interaction and statistical analysis of lattice systems (with discussion). J R Stat Soc Ser B Stat Methodol 36(2):192–236
Besag J (1975) Statistical analysis of non-lattice data. J R Stat Soc D 24(3):179–195
Besag J (1986) On the statistical analysis of dirty pictures. JRSS B 48(3):259–302
Best NG, Ickstadt K, Wolpert RL (2000) Spatial Poisson regression for health and exposure data measured at disparate resolutions. J Am Stat Assoc 95(452):1076–1088
Blondeau-Patissier D, Brando VE, Oubelkheir K, Dekker AG, Clementson LA, Daniel P (2009) Bio-optical variability of the absorption and scattering properties of the Queensland inshore and reef waters, Australia. J Geophys Res 114:C05003. doi:10.1029/2008JC005039
Brando VE, Dekker AG, Schroeder T, Park YJ, Clementson LA, Steven A, Blondeau-Patissier D (2008) Satellite retrieval of chlorophyll CDOM and NAP in optically complex waters using a semi-analytical inversion based on specific inherent optical properties. A case study for Great Barrier Reef coastal waters. In: Proceedings of the XIX ocean optics conference
Chan KS (1993) Asymptotic behavior of the Gibbs sampler. J Am Stat Assoc 88(421):320–326
Cox DR (1955) Some statistical methods connected with series of events. JRSS B 17(2):129–164
Cressie N, Wikle C (2011) Statistics for spatio-temporal data. Wiley, New York
Cucala J, Marin JM, Robert CP, Titterington DM (2009) A Bayesian reassessment of nearest-neighbour classification. J Am Stat Assoc 104(485):263–273
de Berg M, van Kreveld M, Overmars M, Schwarzkopf O (2000) Computational geometry: algorithms and applications, 2nd edn. Springer, Berlin
Dempster A, Laird N, Rubin D (1977) Maximum likelihood from incomplete data via the EM algorithm. JRSS B 39(1):1–38
Denham R, Falk M, Mengersen K (2011) The Bayesian conditional independence model for measurement error: applications in ecology. Environ Ecol Stat 18:239–255
Denison DGT, Adams NM, Holmes CC, Hand DJ (2002) Bayesian partition modelling. Comput Stat Data Anal 38(4):475–485
Denison DGT, Holmes CC (2001) Bayesian partitioning for estimating disease risk. Biometrics 57(1):143–149
Engen S (1978) Stochastic abundance models, with emphasis on biological communities and species diversity., Monographs on applied probability and statisticsChapman and Hall, London
Ferguson T (1973) A Bayesian analysis of some nonparametric problems. Ann Stat 1(2):209–230
Friel N, Pettitt AN (2004) Likelihood estimation and inference for the autologistic model. J Comput Graph Stat 13(1):232–246
Gelfand A (1996) Model determination using sampling based methods. In: Gilks W, Richardson S, Spiegehalter D (eds) Markov Chain Monte Carlo in Practice, chap 9. Chapman and Hall, Boca Raton, FL
Gelfand AE, Smith AFM (1990) Sampling-based approaches to calculating marginal densities. J Am Stat Assoc 85(410):398–409
Geman S, Geman D (1984) Stochastic relaxation, Gibbs distributions and the Bayesian restoration of images. IEEE Trans PAMI 6:721–741
Gilks W, Richardson S, Spiegelhalter D (eds) (1996) Markov chain Monte Carlo in practice., Interdisciplinary statistics seriesChapman & Hall/CRC Press, Boca Raton
Goldsmith J, Wand MP, Crainceanu C (2011) Functional regression via variational Bayes. Electron J Stat 5:572–602
Green P, Richardson S (2002) Hidden Markov models and disease mapping. J Am Stat Assoc 97(460):1055–1070
Green PJ (1995) Reversible jump Markov chain Monte Carlo computation and Bayesian model determination. Biometrika 82(4):711–732
Grenander U (1983) Tutorial in Pattern Theory. Technical report, Division of Applied Mathematics. Brown University
Grenander U, Miller M (2007) Pattern theory: from representation to inference. Oxford University Press, Oxford
Hastings WK (1970) Monte Carlo sampling methods using Markov chains and their applications. Biometrika 57(1):97–109
Heron EA, Walsh CD (2008) A continuous latent spatial model for crack initiation in bone cement. J R Stat Soc Ser C Appl Stat 57(1):25–42
Ickstadt K, Wolpert R (1999) Spatial regression for marked point processes (with discussion). In: Bernado J, Berger J, Dawid A, Smith A (eds) Bayesian statistics 6. Oxford University Press, Oxford, pp 323–341
Illian JB, Sørbye SH, Rue H (2012) A toolbox for fitting complex spatial point process models using integrated nested Laplace approximation (INLA). Ann Appl Stat 6(4):1499–1530
Jordan M, Ghahramani Z, Jaakkola T, Saul L (1999) An introduction to variational methods for graphical models. Mach Learn 37:183–233
Lang S, Brezger A (2004) Bayesian P-Splines. J Comput Graph Stat 13(1):183–212
Leonte D, Nott DJ (2006) Bayesian spatial modelling of gamma ray count data. Math Geol 38(2):135–154
Liang S, Banerjee S, Carlin BP (2009) Bayesian wombling for spatial point processes. Biometrics 65(4):1243–1253
Lindgren F, Rue H, Lindström J (2011) An explicit link between Gaussian fields and Gaussian Markov random fields: the stochastic partial differential equation approach. J R Stat Soc B 73:423–498
Lu H, Carlin BP (2005) Bayesian areal wombling for geographical boundary analysis. Geogr Anal 37(3):265–285
Ma H, Carlin BP (2007) Bayesian multivariate areal wombling for multiple disease boundary analysis. Bayesian Anal 2(2):281–302
Marin J-M, Robert C (2007) Bayesian core: a practical approach to computational Bayesian statistics., Springer Texts in StatisticsSpringer, Berlin
Martin A, Quinn K, Park J (2011) MCMCpack: Markov chain Monte Carlo in R. J Stat Softw 42(9):1–21
Matérn B (1960) Spatial variation. stochastic models and their application to some problems in forest surveys and other sampling investigations. Meddelanden fran statens Skogsforskningsinstitut 49:1–144
McGrory CA, Titterington DM, Reeves R, Pettitt AN (2009) Variational Bayes for estimating the parameters of a hidden Potts model. Stat Comput 19(3):329–340
Mengersen KL, Tweedie RL (1996) Rates of convergence of the Hastings and Metropolis algorithms. Ann Stat 24(1):101–121
Metropolis N, Rosenbluth AW, Rosenbluth MN, Teller AH, Teller E (1953) Equation of state calculations by fast computing machines. J Chem Phys 21(6):1087–1092
Møller J, Pettitt AN, Reeves R, Berthelsen KK (2006) An efficient Markov chain monte carlo method for distributions with intractable normalising constants. Biometrika 93(2):451–458
Møller J, Syversveen A, Waagepetersen R (1998) Log Gaussian Cox processes. Scand J Stat 25(3):451–482
Møller J, Waagepetersen R (2004) Statistical inference and simulation for spatial point processes. Chapman & Hall/CRC Press, Boca Raton
Neal RM (2003) Slice sampling. Ann Stat 31(3):705–741
Nicholls GK (1998) Bayesian image analysis with Markov chain Monte Carlo and coloured continuum triangulation models. JRSS B 60(3):643–659
Okabe A, Boots B, Sugihara K, Chiu SN (2000) Spatial tessellations: concepts and applications of Voronoi diagrams, 2nd edn. Wiley, Chichester
Orbanz P, Buhmann, J (2006) Smooth image segmentation by nonparametric Bayesian inference. In: Proceedings of the ECCV 2006, volume 3951 of Lecture Notes in Computer Science. Springer, Berlin, Heidelberg, pp 444–457
Ormerod JT, Wand MP (2010) Explaining variational approximations. Am Stat 64(2):140–153
O’Rourke J (1998) Computational geometry in C, 2nd edn. Cambridge University Press, Cambridge
Pitman J, Yor M (1997) The two-parameter Poisson-Dirichlet distribution derived from a stable subordinator. Ann Probab 25(2):855–900
Plummer M (2003) JAGS: a program for analysis of Bayesian graphical models using Gibbs sampling. In Hornik K, Leisch F, Zeileis A (eds) Proceedings of the 3rd international workshop on distributed statistical computing
Potts RB (1952) Some generalized order-disorder transitions. Proc Camb Philos Soc 48:106–109
Robert C, Casella G (2004) Monte Carlo statistical methods, 2nd edn., Springer Texts in StatisticsSpringer, New York
Rue H (2001) Fast sampling of Gaussian Markov random fields. JRSS B 63(2):325–338
Rue H, Held L (2005) Gaussian Markov random fields: theory and applications, volume 104 of Monographs on statistics and applied probability. Chapman & Hall/CRC Press, Boca Raton
Rue H, Martino S (December, 2010) INLA: functions which allow to perform a full Bayesian analysis of structured additive models using Integrated Nested Laplace Approximaxion (0.0 ed.)
Rue H, Martino S, Chopin N (2009) Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations. J R Stat Soc B 71:319–392
Rue H, Tjelmeland H (2002) Fitting Gaussian Markov random fields to Gaussian fields. Scand J Stat 29(1):31–49
Rydén T, Titterington D (1998) Computational Bayesian analysis of hidden Markov models. J Comput Graph Stat 7(2):194–211
Shyr A, Darrell T, Jordan M, Urtasun R (2011) Supervised hierarchical Pitman-Yor process for natural scene segmentation. In: Proceedings of the IEEE CVPR, pp 2281–2288
Smith M, Kohn R (1996) Nonparametric regression using Bayesian variable selection. J Econom 75(2):317–343
Strickland C, Denham R, Alston C, Mengersen K (2012) A Python package for Bayesian estimation using Markov chain Monte Carlo. In: Alston C, Mengersen K, Pettitt A (eds) Case atudies in Bayesian statistical modelling and analysis. Wiley, New York, pp 421–460
Sudderth E, Jordan M (2009) Shared segmentation of natural scenes using dependent Pitman-Yor processes. Proc NIPS 21:1585–1592
Tanner MA, Wong WH (1987) The calculation of posterior distributions by data augmentation. J Am Stat Assoc 82(398):528–540
Teh Y, Jordan M, Beal M, Blei D (2006) Hierarchical Dirichlet processes. J Am Stat Assoc 101(476):1566–1581
Thomas A, Best N, Lunn D, Spiegelhalter D (2012) The BUGS book: a practical introduction to Bayesian analysis, volume 98 of Chapman & Hall/CRC Texts in Statistical Science. Taylor & Francis, London
Tierney L, Kadane JB (1986) Accurate approximations for posterior moments and marginal densities. J Am Stat Assoc 81(393):82–86
Winkler G (2003) Image analysis, random fields and Markov Chain Monte Carlo methods: a mathematical introduction 2nd edn. Springer, Berlin
Wolpert RL, Ickstadt K (1998a) Poisson/gamma random field models for spatial statistics. Biometrika 85(2):251–267
Wolpert RL, Ickstadt K (1998b) Simulation of Lévy Random Fields. In: Müller P, Dey D, Sinha D (eds) Practical nonparametric and semiparametric Bayesian statistics. Springer, Berlin, pp 227–242
Acknowledgments
The authors would like to thank Dr. Andy Steven, CSIRO, for the data used in this paper. The authors would also like to thank two anonymous reviewers for their comments which greatly improved the manuscript. The research was funded from an Australian Research Council (ARC) Linkage Grant (LP0668185) and by the ARC Centre of Excellence for Complex Dynamic Systems and Control (CDSC).
Author information
Authors and Affiliations
Corresponding author
Additional information
Handling Editor: Pierre Dutilleul.
Rights and permissions
About this article
Cite this article
Falk, M.G., Alston, C.L., McGrory, C.A. et al. Recent Bayesian approaches for spatial analysis of 2-D images with application to environmental modelling. Environ Ecol Stat 22, 571–600 (2015). https://doi.org/10.1007/s10651-015-0311-1
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10651-015-0311-1