Title :
Bond percolation-based Gibbs-Markow random fields for image segmentation
Author :
Hussain, Iftekhar ; Reed, Todd R.
Author_Institution :
Dept. of Electr. & Comput. Eng., California Univ., Davis, CA, USA
Abstract :
A new bond percolation-based approach is presented to determine the clique potential parameters of a Gibbs-Markov random field (GMRF) model used in image segmentation. Previously, experimentally determined fixed values were used for these parameters independent of the underlying image. Using the proposed approach, these parameters are now derived as a function of local characteristics of the image under consideration. An additional salient feature of this method is its suitability for a renormalization group approach to multi-scale description of the clique potential parameters.<>
Keywords :
Markov processes; image segmentation; parameter estimation; random processes; renormalisation; bond percolation-based Gibbs-Markow random fields; clique potential parameters; image segmentation; local characteristics; multi-scale description; renormalization group approach; Bonding; Computer simulation; Image segmentation; Laboratories; Lattices; Nearest neighbor searches; Pixel; Signal processing; TV;
Journal_Title :
Signal Processing Letters, IEEE