Title :
Stochastic processes that generate polygonal and related random fields
Author :
Borkar, Vivek S. ; Mitter, Sanjoy K.
Author_Institution :
Dept. of Electr. Eng., Indian Inst. of Sci., Bangalore, India
fDate :
3/1/1996 12:00:00 AM
Abstract :
A reversible, ergodic, Markov process taking values in the space of polygonally segmented images is constructed. The stationary distribution of this process can be made to correspond to a Gibbs-type distribution for polygonal random fields as introduced by Arak and Surgailis (1989) and a few variants thereof, such as those arising in Bayesian analysis of random fields. Extensions to generalized polygonal random fields are presented where the segmentation boundaries are not necessarily straight line segments
Keywords :
Bayes methods; Markov processes; image segmentation; random processes; Bayesian analysis; Gibbs-type distribution; polygonal random fields; polygonally segmented images; random fields; reversible ergodic Markov process; segmentation boundaries; stationary distribution; stochastic processes; straight line segments; Image processing; Image segmentation; Random sequences; Reflection; Stochastic processes; Symmetric matrices; Topology;
Journal_Title :
Information Theory, IEEE Transactions on
