Stochastic Segmentation Using Gibbs Priors
Eilat Vardi, Gábor T. Herman · Electronic Notes in Theoretical Computer Science · 2001
In earlier work, a fast stochastic method for reconstructing a certain class of two-dimensional binary images from projections using Gibbs priors was presented. In the present study, we introduce a stochastic segmentation of magnetic resonance gray-scale images of trabecular bone using Gibbs priors. We show some results as well as some post-processing that can be used to clean up segmentations of noisy gray-scale images.