Classification algorithms integrated with convolutional neural networks (CNN) display high accuracies in synthetic aperture radar (SAR) image classification. However, their consideration of spatial information is not comprehensive and effective, which causes poor performance edges complex regions. This paper proposes a Markov random field (MRF)-based algorithm for SAR classification fully consi...

Superpixels have become prevalent in computer vision. They have been used to achieve satisfactory performance at a significantly smaller computational cost for various tasks. People have also combined superpixels with Markov random field (MRF) models. However, it often takes additional effort to formulate MRF on superpixellevel, and to the best of our knowledge there exists no principled approa...

Quantitative assessment of trabecular bone structure based on magnetic resonance microimages requires a segmentation step, which is difficult to perform because of low signal-to-noise ratio and spatial signal inhomogeneities in these images. In this paper, we present the design of voxel classifiers based on statistical mixture models and classifiers using the feed-forward artificial neural netw...

A Extended derivations and proofs A.1 Markov random field reformulation We prove in this section that under the Rich Sufficient Statistics condition (RSS)1, the log-partition function is the same in the original exponential family and in the bipartite MRF described in Section 2.2. Let us denote the latter log-partition function by Ã(θ). We first prove the following identity, introduced in the m...

The problem we address in this paper is to label datapoints when the information about them is provided primarily in terms of their subsets or groups. The knowledge we have for a group is a likelihood value for each group member to belong to same class. These likelihood values are computed using a model, either explicit or implicit, of the pattern we wish to learn. By defining a Markov Random F...

This paper presents CIS, a biomedical simulation framework based on the markov random field (MRF). CIS is a discrete domain 2-D simulation framework emphasizing on the spatial interactions of biomedical entities. The probability model within the MRF framework facilitates the construction of more realistic models than deterministic differential equation approaches and cellular automata. The glob...

We propose a Markov Random Field based image segmentation method which integrates domain specific information into MRF energy. The proposed segmentation method assumes that there is no labeled training set, but some priori general information referred as domain specific information about the dataset, is available. Domain specific information is received from a domain expert and formalized by a ...

A new method for the automated extraction of pipelines and roads from Synthetic Aperture Radar (SAR) scenes is presented. It combines intensity data with coherence data from an interferometric evaluation of a SAR scene pair. The fusion is based on Bayesian statistics and part of a Markov random field (MRF) model for line extraction. Both, intensity and coherence data are evaluated using rotatin...

This paper proposes some Markov Random Field (MRF) models for restoration of stereo disparity maps. The main aspect is the use of confidence maps provided by the Symmetric Multiple Windows (SMW) stereo algorithm to guide the restoration process. The SMW algorithm is an adaptive, multiple-window scheme using left-right consistency to compute disparity and its associated confidence in presence of...

In this paper we present Markov random field (MRF) models for face occlusion detection and recovery. For occlusion detection, we use a pixel-based pair-wise MRF model (which is similar to the Ising model) where the binary mask on each pixel is inferred to decide the presence of occlusion. Then we construct a patch-based nonparametric pair-wise MRF model for occlusion recovery, which is learned ...