# Unsupervised Bayesian wavelet domain segmentation using Potts-Markov random field modeling

@article{Brault2005UnsupervisedBW, title={Unsupervised Bayesian wavelet domain segmentation using Potts-Markov random field modeling}, author={Patrice Brault and Ali Mohammad-Djafari}, journal={J. Electronic Imaging}, year={2005}, volume={14}, pages={043011} }

We describe a new fully unsupervised image segmentation method based on a Bayesian approach and a Potts-Markov random field (PMRF) model that are performed in the wavelet domain. A Bayesian segmentation model, based on a PMRF in the direct domain, has already been successfully developed and tested. This model performs a fully unsupervised segmentation, on images composed of homogeneous regions, by introducing a hidden Markov model (HMM) for the regions to be classified, and Gaussian…

## 6 Citations

### Scalable Region‐matching Motion Estimation Based on an Unsupervised Spatial Segmentation

- Computer Science
- 2006

It is shown that a hierarchical, region‐based, ME, can provide an interesting approach w.r.t. the necessity of ME robustness as well as its scalability, in a region (or object) ‐based compression scheme.

### Extraction of Active Regions and Coronal Holes from EUV Images Using the Unsupervised Segmentation Method in the Bayesian Framework

- Physics
- 2016

The solar corona is the origin of very dynamic events that are mostly produced in active regions (AR) and coronal holes (CH). The exact location of these large-scale features can be determined by…

### Bayesian approach with prior models which enforce sparsity in signal and image processing

- Computer Science, MathematicsEURASIP J. Adv. Signal Process.
- 2012

This review article proposes to use the Bayesian inference approach for inverse problems in signal and image processing, where the authors want to infer on sparse signals or images, and considers the probabilistic models to enforce the sparsity.

### A New Bayesian Edge-Linking Algorithm Using Single-Target Tracking Techniques

- Computer ScienceSymmetry
- 2016

These proposed algorithms transform the conventional edge-linking problem into a single-target tracking problem, which is a well-known problem in object tracking, and apply sophisticated Bayesian inference to connect the edge points.

### Estimation de mouvement et segmentation d'image

- Physics
- 2005

La premiere partie de ce memoire presente une nouvelle vision de l'estimation de mouvement (EM) dans les sequences video. Nous abordons l'EM a partir de familles d'ondelettes redondantes peu connues…

### Estimation de mouvement et segmentation Partie I : Estimation de mouvement par ondelettes spatio-temporelles adaptées au mouvement. Partie II : Segmentation et estimation de mouvement par modèles de Markov cachés et approche bayésienne dans les domaines direct et ondelette.

- Philosophy
- 2005

La premiere partie de ce memoire presente une nouvelle vision de l'estimation de mouvement, et donc de la compression, dans les sequences video. D'une part, nous avons choisi d'aborder l'estimation…

## References

SHOWING 1-10 OF 29 REFERENCES

### Bayesian Wavelet Domain Segmentation

- Computer Science
- 2004

A new version of the fully unsupervised segmentations of still images and 2D+T sequences is demonstrated by Bayesian methods, on the basis of a Hidden Markovian Model and a Potts‐Markov Random Field, in the pixel domain by taking advantage of the local decay property, or “peaky” distribution of the wavelet coefficients, in an orthogonal decomposition.

### A multiscale random field model for Bayesian image segmentation

- Computer Science, MathematicsIEEE Trans. Image Process.
- 1994

Simulations on synthetic images indicate that the new algorithm performs better and requires much less computation than MAP estimation using simulated annealing, and is found to improve classification accuracy when applied to the segmentation of multispectral remotely sensed images with ground truth data.

### Bayesian segmentation and motion estimation in video sequences using a Markov-Potts model

- Mathematics, Computer Science
- 2004

A new approach for the segmentation of video sequences based on recent works on the Bayesian segmentation and fusion is reported here, making the assumption that the images follow a Potts-Markov random field model.

### Unsupervised image segmentation using wavelet-domain hidden Markov models

- Computer ScienceSPIE Optics + Photonics
- 2003

A new unsupervised segmentation approach is developed by capturing the likelihood disparity of different texture features with respect to wavelet-domain HMMs, where three clustering methods are used to obtain the initial segmentation results.

### Multiscale Bayesian segmentation using a trainable context model

- Computer ScienceIEEE Trans. Image Process.
- 2001

A multiscale Bayesian segmentation algorithm which can effectively model complex aspects of both local and global contextual behavior is proposed which makes the method flexible by allowing both the context and the image models to be adapted without modification of the basic algorithm.

### Multiscale image segmentation using wavelet-domain hidden Markov models

- Computer ScienceIEEE Trans. Image Process.
- 2001

A new image texture segmentation algorithm, HMTseg, based on wavelets and the hidden Markov tree model, which can directly segment wavelet-compressed images without the need for decompression into the space domain.

### Bayesian tree-structured image modeling using wavelet-domain hidden Markov models

- Computer ScienceOptics & Photonics
- 1999

This paper proposes a fast shift-invariant HMT estimation algorithm that outperforms all other wavelet- based estimators in the current literature, both in mean- square error and visual metrics.

### Image fusion and unsupervised joint segmentation using a HMM and MCMC algorithms

- Computer Science, MathematicsJ. Electronic Imaging
- 2005

A Bayesian framework for unsupervised image fusion and joint segmentation based on a hidden Markov modeling of the images where the hidden variables represent the common classification or segmentation labels is proposed.

### Mean field annealing using compound Gauss-Markov random fields for edge detection and image estimation

- Computer ScienceIEEE Trans. Neural Networks
- 1993

A deterministic relaxation method based on mean field annealing with a compound Gauss-Markov random (CGMRF) field model is proposed and a set of iterative equations for the mean values of the intensity and both horizontal and vertical line processes with or without taking into account some interaction between them are presented.

### Graduated nonconvexity algorithm for image estimation using compound Gauss Markov field models

- Computer ScienceInternational Conference on Acoustics, Speech, and Signal Processing,
- 1989

The authors describe the development of a deterministic algorithm for obtaining the global maximum a posteriori probability (MAP) estimate from an image corrupted by additive Gaussian noise that finds the global MAP estimate in a small number of iterations.