In this report we show, that an arbitrary MinSum problem (i. e. a MinSum problem with an arbitrary finite set of states) can be adequat ly transformed into a binary one (i.e. into a MinSum problemâ€¦ (More)

During the last decades a lot of applied structural recognition problems came to light which might be reduced to consistent labelling problems. The consistent labelling problem and its appropriateâ€¦ (More)

Many image recognition tasks can be expressed in terms of searching for the maximum a posteriori labeling in some statistical model. We introduce a class of higher order Gibbs models, also known asâ€¦ (More)

We propose a probabilistic segmentation scheme, which is widely applicable to some extend. Besides the segmentation itself our model incorporates object specific shading. Dependent upon application,â€¦ (More)

We propose a combination of shape prior models with Markov Random Fields. The model allows to integrate multiple shape priors and appearance models into MRF-models for segmentation. We discuss aâ€¦ (More)

We analyse the potential of Gibbs Random Fields for shape prior modelling. We show that the expressive power of second order GRFs is already sufficient to express spatial relations between shapeâ€¦ (More)

We consider the task of stereo-reconstruction under the following fairly broad assumptions. A single and continuously shaped object is captured by two uncalibrated cameras. It is assumed, that almostâ€¦ (More)

We propose a feed-forward inference method applicable to belief and neural networks. In a belief network, the method estimates an approximate factorized posterior of all hidden units given the input.â€¦ (More)

IEEE Transactions on Pattern Analysis and Machineâ€¦

2013

The aim of this short note is to draw attention to a method by which the partition function and marginal probabilities for a certain class of random fields on complete graphs can be computed inâ€¦ (More)