Experiments with morphological Marcov random fields

• Autorzy: Nieniewski, M.
• Konferencja: Conference on Computer Graphics and Image Processing, GKPO' 98 (5 ; 18-22.05.1998 ; Borki, Poland)
• Języki publikacji: EN

Abstrakty

EN

The paper presents results of experiments whit morphologacal Marcov Random Fields (MRFs). The use of MRFs allows one to include a prior knowledge about an image via the probability model into the processing of the image. At the same time, when generating random textures, one notes thet various textures are possible, for which the models still have to be invented. The morphologicalMRFs offer a method for enlarging the set of propability models. However, it is not obvious what the effects of changing the model and its parameters will be. The paper presents results of systematic experiments whit the generalized Ising model as well as generalized Potts model. Inthis way a deeper insight into the properties of the morphological MRFs is obtained.

• Czasopismo: Machine Graphics and Vision
• Rocznik: 1998
• Tom: Vol. 7, No. 1/2
• Strony: 205-222
• Opis fizyczny: Bibliogr. 13 poz.

Twórcy

autor

Nieniewski, M.

• Dep. of Fund. Res. in EE, PAS; Inst. of Fund. Tech. Res., PAS; Warsaw,