Academic Journals Database
Disseminating quality controlled scientific knowledge

Reference Fields Analysis of a Markov Random Field Model to Improve Image Segmentation

ADD TO MY LIST
 
Author(s): E. D. López-Espinoza | L. Altamirano-Robles

Journal: Journal of Applied Research and Technology
ISSN 1665-6423

Volume: 8;
Issue: 2;
Start page: 260;
Date: 2010;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: Image segmentation | unsupervised segmentation | Markov random field | non-homogeneous random field.

ABSTRACT
In Markov random field (MRF) models, parameters such as internal and external reference fields are used. In thispaper, the influence of these parameters in the segmentation quality is analyzed, and it is shown that, for imagesegmentation, a MRF model with a priori energy function defined by means of non-homogeneous internal andexternal field has better segmentation quality than a MRF model defined only by a homogeneous internal referencefield. An analysis of the MRF models in terms of segmentation quality, computational time and tests of statisticalsignificance is done. Significance tests showed that the segmentations obtained with MRF model defined by means ofnon-homogeneous reference fields are significant at levels of 85% and 75%.
Save time & money - Smart Internet Solutions     

Tango Rapperswil
Tango Rapperswil