Content deleted Content added
m Delete stray word introduced by IP vandal in edits 1025214856 and 1025214972; the replaced word "with" was long ago restored |
|||
Line 276:
A range of other methods exist for solving simple as well as higher order MRFs. They include Maximization of Posterior Marginal, Multi-scale MAP estimation,<ref>A. Bouman and M. Shapiro (2002): "A multiscale Random field model for Bayesian image segmentation", IEEE Transactions on Image Processing, pp. 162–177, Vol. 3.</ref> Multiple Resolution segmentation<ref>J. Liu and Y. H. Yang (1994): "[https://ieeexplore.ieee.org/abstract/document/297949/ Multiresolution color image segmentation]", IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 689–700, Vol. 16.</ref> and more. Apart from likelihood estimates, graph-cut using maximum flow<ref>S. Vicente, V. Kolmogorov and C. Rother (2008): "[http://www0.cs.ucl.ac.uk/staff/s.vicente/papers/connectedGC-CVPR08-TR.pdf Graph cut based image segmentation with connectivity priors]", CVPR</ref> and other highly constrained graph based methods<ref>Corso, Z. Tu, and A. Yuille (2008): "MRF Labelling with Graph-Shifts Algorithm", Proceedings of International workshop on combinatorial Image Analysis</ref><ref>B. J. Frey and D. MacKayan (1997): "[http://papers.nips.cc/paper/1467-a-revolution-belief-propagation-in-graphs-with-cycles.pdf A Revolution: Belief propagation in Graphs with Cycles]", Proceedings of Neural Information Processing Systems (NIPS)</ref> exist for solving MRFs.
==== Image segmentation using
The [[expectation–maximization algorithm]] is utilized to iteratively estimate the a posterior probabilities and distributions of labeling when no training data is available and no estimate of segmentation model can be formed. A general approach is to use histograms to represent the features of an image and proceed as outlined briefly in this three-step algorithm:
| |||