Isotropic Properties of Some Multi-body Interaction Models: Two Quality Criteria for Markov Priors in Image Processing - Inria - Institut national de recherche en sciences et technologies du numérique
Reports Year : 1999

Isotropic Properties of Some Multi-body Interaction Models: Two Quality Criteria for Markov Priors in Image Processing

Xavier Descombes
Eugene Pechersky
  • Function : Author
  • PersonId : 833592

Abstract

Gibbs Fields are widely used in image processing for both segmentation and restoration. Defined on a discrete lattice representing the image they exhibit a non-isotropic behavior. Herein, we study and quantify this non-isotropy by computing the boundary tension as a function of the angle of a line separating the plane in two parts containing a different phase. From this study, we derive two quantitative criteria of the non isotropy of the model. We then compute the shape at zero temperature of a droplet of one phase within the other phase and study the non-isotropy of the shape for the different models. Finally, we show the artifacts due to this non-isotropic behavior for image segmentation and restoration.
Fichier principal
Vignette du fichier
RR-3752.pdf (382.1 Ko) Télécharger le fichier

Dates and versions

inria-00072910 , version 1 (24-05-2006)

Identifiers

  • HAL Id : inria-00072910 , version 1

Cite

Xavier Descombes, Eugene Pechersky. Isotropic Properties of Some Multi-body Interaction Models: Two Quality Criteria for Markov Priors in Image Processing. RR-3752, INRIA. 1999. ⟨inria-00072910⟩
157 View
78 Download

Share

More