Stochastic Segmentation of Severely Degraded Images Using Gibbs Random Fields

DOI PDF Web Site Web Site BIBCODE 22 References
  • KIM Dong–Woo
    Department of Physics, Korea Advanced Institute of Science and Technology, Taejon 305–701, Republic of Korea
  • LEE Gee–Hyuk
    Department of Physics, Korea Advanced Institute of Science and Technology, Taejon 305–701, Republic of Korea
  • KIM Soo–Yong
    Department of Physics, Korea Advanced Institute of Science and Technology, Taejon 305–701, Republic of Korea

Search this article

Description

This paper deals with segmentation of noisy images using Gibbs random field (GRF) with an emphasis on modeling of the region process. For noisy image segmentation using the multi-level logistic (MLL) model with the second-order neighborhood system, which is commonly used in image processing, the segmentation performance is degraded significantly in case of low signal to noise ratio. By comparison with the Ising model that explains the magnetic properties of ferromagnetic material, it is evident that the characteristics of the region process modeled using the MLL model with the second-order neighborhood system are different in nature from the expected characteristics of a region. To solve this problem we added the term of the magnetic energy associated with the magnetic field of a spin system (or image) to the energy function of GRF. Using the modified model for the region process, the result of image segmentation was improved and did not depend on the cooling schedule in simulated annealing.

Journal

  • Optical Review

    Optical Review 3 (3), 184-191, 1996

    Japan Society of Applied Physics

References(22)*help

See more

Keywords

Details 詳細情報について

Report a problem

Back to top