Relaxation labelling

Relaxation labelling is an image treatment methodology. Its goal is to associate a label to the pixels of a given image or nodes of a given graph.

Papers overview

Semantic Scholar uses AI to extract papers important to this topic.

2010

This paper proposes the sequential context inference (SCI) algorithm for Markov random field (MRF) image analysis. This algorithm…

2008

In this paper, a new strategy is proposed to defend against colluding malicious nodes in a sensor network. The strategy is based…

2006

In this paper a new formulation of probabilistic relaxation labeling is developed using the theory of diffusion processes on…

2005

This paper describes a scheme for reconstructing 3D human models from whole-body scan data. The 3D human models are composed of…

2000

We address the problem of object recognition in computer vision. We propose an invariant representation of the model and scene in…

1999

Ordinal measures, based on the relative order of intensity values within window, provide a robust method for finding…

1998

The main aim of this work is to propose a new artificial neural network architecture to solve the motion correspondence problem…

1989

Review

1987

Review

1987

The use of optimisation approaches for relaxation labelling is reviewed and its relationship to earlier heuristic schemes is…

1982