This article proposes a new multispectral image texture segmentation algorithm using a multi-resolution fuzzy Markov random field model for a variable scale in the wavelet domain. The algorithm considers multi-scalar information in both vertical and lateral directions. The feature field
of the scalable wavelet coefficients is modelled, combining with the fuzzy label field describing the spatially constrained correlations between neighbourhood features to achieve a more accurate parameter estimation. The extended scalable label field models the label data from different scales
to obtain more homogeneous areas; image segmentation results are finally obtained according to the Bayesian rule from a coarser to a finer scale. Multispectral texture images and remote-sensing images are used to test the effectiveness of the the proposed method. Segmentation results show
that the new method simultaneously presents a better performance in achieving the homogeneity of the region and accuracy of detected boundaries compared with existing image segmentation algorithms.
No Reference information available - sign in for access.
No Citation information available - sign in for access.
No Supplementary Data.
No Article Media
Document Type: Research Article
Affiliations:1: College of Resources Environment & Tourism, Capital Normal University, Beijing, 100048, PR China 2: Department of Geoinformatics, University of Salzburg, 5020, Salzburg, Austria