A systematic way for region-based image segmentation based on Markov Random Field model

https://doi.org/10.1016/0167-8655(94)90028-0Get rights and content

Abstract

In this paper, we propose a Markov Random Field model-based approach as a systematic way for integrating constraints for robust image segmentation. In our approach, the image is first segmented into a set of disjoint regions by one of the region-based segmentation techniques which operates on image pixels, and a Region Adjaceny Graph (RAG) is then constructed from the resulting segmented regions based on the spatial adjacencies between regions. Our approach is then applied by defining an MRF model on the corresponding RAG. Constraints for improving the segmentation results are incorporated into an energy function via clique functions and optimal segmentation is then achieved by finding a labeling configuration which minimizes the energy function through simulated annealing.

References (12)

  • R.M. Haralick et al.

    Image segmentation techniques

    Computer Vision, Graphics, and Image Processing

    (1985)
  • M.S. Suk et al.

    A new image segmentation technique based on Partition Mode Test

    Pattern Recognition

    (1983)
  • M.J. Daily

    Color image segmentation using Markov Random Field

  • H. Derin et al.

    Bayes smoothing algorithms for segmentation of binary images modeled by Markov Random Fields

    IEEE Trans. Pattern Anal. Machine Intell.

    (1984)
  • R.C. Dubes et al.

    MRF model based akgorithms for image segmentation

  • E.B. Gamble et al.

    Integration of vision modules and labeling of surface discontinuities

    IEEE Trans. Syst. Man Cybernet.

    (1989)
There are more references available in the full text version of this article.

Cited by (0)

View full text