A Bayesian segmentation methodology for parametric image models
- 1 January 1995
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 17 (2) , 211-217
- https://doi.org/10.1109/34.368166
Abstract
Region-based image segmentation methods require some criterion for determining when to merge regions. This paper presents a novel approach by introducing a Bayesian probability of homogeneity in a general statistical context. Our approach does not require parameter estimation and is therefore particularly beneficial for cases in which estimation-based methods are most prone to error: when little information is contained in some of the regions and, therefore, parameter estimates are unreliable. We apply this formulation to three distinct parametric model families that have been used in past segmentation schemes: implicit polynomial surfaces, parametric polynomial surfaces, and Gaussian Markov random fields. We present results on a variety of real range and intensity images.Keywords
This publication has 27 references indexed in Scilit:
- Real-time recognition with the entire Brodatz texture databasePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A Review of Recent Texture Segmentation and Feature Extraction TechniquesComputer Vision and Image Understanding, 1993
- Segmentation of 3D Range Images Using Pyramidal Data StructuresComputer Vision and Image Understanding, 1993
- Bayes Factors for Outlier Models Using the Device of Imaginary ObservationsJournal of the American Statistical Association, 1992
- Maximum likelihood unsupervised textured image segmentationCVGIP: Graphical Models and Image Processing, 1992
- Bayesian modeling of uncertainty in low-level visionInternational Journal of Computer Vision, 1990
- Bayesian clustering for unsupervised estimation of surface and texture modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1988
- Segmentation through variable-order surface fittingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1988
- Simple Parallel Hierarchical and Relaxation Algorithms for Segmenting Noncausal Markovian Random FieldsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1987
- On Optimally Combining Pieces of Information, with Application to Estimating 3-D Complex-Object Position from Range DataPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1986