On Estimating Granulometric Discrete Size Distributions of Random Sets
- 362 Downloads
Morphological granulometries, and the associated size distributions and densities, are important shape/size summaries for random sets. They have been successfully employed in a number of image processing and analysis tasks, including shape analysis, multiscale shape representation, texture classification, and noise filtering. For most random set models however it is not possible to analytically compute the size distribution. In this contribution, we investigate the problem of estimating the granulometric (discrete) size distribution and size density of a discrete random set. We propose a Monte Carlo estimator and compare its properties with that of an empirical estimator. Theoretical and experimental results demonstrate superiority of the Monte Carlo estimation approach. The Monte Carlo estimator is then used to demonstrate existence of phase transitions in a popular discrete random set model known as a binary Markov random field, as well as a tool for designing “optimal” filters for binary image restoration.
Key wordsGranulometries Image Restoration Markov Random Fields Mathematical Morphology Monte Carlo Estimation Random Sets Size Distribution Phase Transition
Unable to display preview. Download preview PDF.
- E.R. Dougherty and Y. ChenLogical granulometric filtering in the signalunion-clutter modelThis Volume, pp. 73–95.Google Scholar
- E.R. Dougherty and J.B. PelzMorphological granulometric analysis of electrophotographic images - Size distribution statistics for process controlOptical Engineering, 30 (1991), pp. 438–445.Google Scholar
- B. GirasMetropolis-type Monte Carlo simulation algorithms and simulated annealingTopics in Contemporary Probability and its Applications (J.L. Snell, ed.), Boca Raton, Florida: CRC Press, 1995, pp. 159–232.Google Scholar
- J.J. Binney, N.J. Dowrick, A.J. Fisher, and M.E.J. NewmanThe Theory of Critical Phenomena: An Introduction to the Renormalization GroupOxford University Press, Oxford, England, 1992.Google Scholar
- D. RuelleStatistical Mechanics: Rigorous ResultsAddison-Wesley, Reading, Massachusetts, 1983.Google Scholar
- H.J.A.M. HeijmansMorphological Image OperatorsAcademic Press, Boston, Massachusetts, 1994.Google Scholar
- J. Mattioli and M. SchmittOn information contained in the erosion curveShape in Picture: Mathematical Description of Shape in Grey-level Images (Y.L.O.A. Toet, D. Foster, H.J.A.M. Heijmans, and P. Meer, eds.), Berlin, Germany: Springer-Verlag, 1994, pp. 177–195.Google Scholar
- G. PotamianosStochastic Simulation Algorithms for Partition Function Estimation of Markov Random Field ImagesPhD Thesis, Department of Electrical and Computer Engineering, The Johns Hopkins University, Baltimore, Maryland, 1994.Google Scholar
- J. GoutsiasMarkov random fields: Interacting particle systems for statistical image modeling and analysisTech. Rep. JHU/ECE 96–01, Department of Electrical and Computer Engineering The Johns Hopkins University Baltimore, Maryland 21218, 1996.Google Scholar