Stochastic annealing for nearest-neighbour point processes with application to object recognition
- 1 June 1994
- journal article
- Published by Cambridge University Press (CUP) in Advances in Applied Probability
- Vol. 26 (2) , 281-300
- https://doi.org/10.2307/1427436
Abstract
We study convergence in total variation of non-stationary Markov chains in continuous time and apply the results to the image analysis problem of object recognition. The input is a grey-scale or binary image and the desired output is a graphical pattern in continuous space, such as a list of geometric objects or a line drawing. The natural prior models are Markov point processes found in stochastic geometry. We construct well-defined spatial birth-and-death processes that converge weakly to the posterior distribution. A simulated annealing algorithm involving a sequence of spatial birth-and-death processes is developed and shown to converge in total variation to a uniform distribution on the set of posterior mode solutions. The method is demonstrated on a tame example.Keywords
This publication has 20 references indexed in Scilit:
- A survey of the hough transformPublished by Elsevier ,2005
- Stochastic geometry models in high-level visionJournal of Applied Statistics, 1993
- ICM for Object RecognitionPublished by Springer Nature ,1992
- An ergodic L2-theorem for simulated annealing in bayesian image reconstructionJournal of Applied Probability, 1990
- Boundary detection by constrained optimizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990
- SCILAIM: A multi-level interactive image processing environmentPattern Recognition Letters, 1990
- On the rate of convergence of spatial birth-and-death processesAnnals of the Institute of Statistical Mathematics, 1989
- Nearest-Neighbour Markov Point Processes and Random SetsInternational Statistical Review, 1989
- Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of ImagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1984
- Markov Point ProcessesJournal of the London Mathematical Society, 1977