A Markov random field model for object matching under contextual constraints
- 1 January 1994
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 866-869
- https://doi.org/10.1109/cvpr.1994.323915
Abstract
This paper presents a Markov random field (MRF) model for object recognition in high level vision. The labeling state of a scene in terms of a model object is considered as an MRF or couples MRFs. Within the Bayesian framework the optimal solution is defined as the maximum a posteriori (MAP) estimate of the MRF. The posterior distribution is derived based on sound mathematical principles from theories of MRF and probability, which is in contrast to heuristic formulations. An experimental result is presented.Keywords
This publication has 6 references indexed in Scilit:
- Parallel structure recognition with uncertainty: coupled segmentation and matchingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Invariant representation, matching and pose estimation of 3D space curves under similarity transformationsPattern Recognition, 1997
- Markov random field models in computer visionLecture Notes in Computer Science, 1994
- A Markov random field model-based approach to image interpretationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1992
- Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of ImagesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1984
- On the Foundations of Relaxation Labeling ProcessesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1983