Title :
A bond percolation-based model for image segmentation
Author :
Hussain, Iftekhar ; Reed, Todd R.
Author_Institution :
Gen. DataComm. Inc., Middlebury, CT, USA
fDate :
12/1/1997 12:00:00 AM
Abstract :
This work presents a novel bond percolation-based approach to determine the clique potential parameters of a Gibbs-Markov model as a function of local characteristics of the underlying image. Using the renormalization group transformation, a multiscale description of the clique potential parameters is formed and used to obtain multiresolution image segmentation
Keywords :
Markov processes; image resolution; image segmentation; parameter estimation; percolation; random processes; renormalisation; transforms; Gibbs-Markov model; bond percolation-based model; clique potential parameters; image segmentation; multiscale description; renormalization group transformation; underlying image; Assembly; Automobiles; Bonding; Cancer detection; Crops; Image resolution; Image segmentation; Machine vision; Nearest neighbor searches; Two dimensional displays;
Journal_Title :
Image Processing, IEEE Transactions on
