Proceedings ArticleDOI
Object point processes for image segmentation
S. Drot,Xavier Descombes,H. Le Men,Josiane Zerubia +3 more
- Vol. 2, pp 913-916
TLDR
This paper studies the application of models from stochastic geometry to the problem of image segmentation by defining an algorithm for their simulation which includes birth or death and geometric transformations of an object in the current configuration.Abstract:
In this paper, we study the application of models from stochastic geometry to the problem of image segmentation The input is a grey-scale image and the desired output is a collection of geometric objects Here, these objects are equilateral triangles The considered priors are pairwise interaction point processes used in stochastic geometry They are chosen so that their realisations are close to partitions of the input image We define an algorithm for their simulation which includes birth or death and geometric transformations of an object in the current configuration Posterior mode solutions are studied by coupling this algorithm with simulated annealing This approach includes post-processing to merge objects of similar radiometryread more
Citations
More filters
Proceedings ArticleDOI
A Gauss-Markov model for hyperspectral texture analysis of urban areas
TL;DR: This paper deals with the problem of texture segmentation using a joint spectral and spatial analysis of pixel distribution using a Markovian model and develops a vectorial approach for this image type.
Dissertation
Méthodes stochastiques en analyse d'image : des champs de Markov aux processus ponctuels marqués
TL;DR: Ce memoire resume mes travaux sur la decennie (entre 1994 et 2003) suivant ma these de doctorat qui etait consacree aux champs de Markov en analyse d'image and fut soutenue en decembre 1993.
Journal ArticleDOI
Extracting Geometric Structures in Images with Delaunay Point Processes
TL;DR: This work introduces Delaunay Point Processes, a framework for the extraction of geometric structures from images that uses Markov Chain Monte Carlo to minimize an energy that balances fidelity to the input image data with geometric priors on the output structures.
Book ChapterDOI
Segmentation of SAR image using mixture multiscale ARMA network
Haixia Xu,Zheng Tian,Fan Meng +2 more
TL;DR: A mixture multiscale autoregressive moving average (ARMA) network is proposed for unsupervised segmentation of synthetic aperture radar (SAR) image and a corresponding learning algorithm is derived based on the Akaike's information criterion (AIC) and genetic algorithm (GA).
Dissertation
Analyse d'image géométrique et morphométrique par diagrammes de forme et voisinages adaptatifs généraux
TL;DR: In this paper, the authors define a set of fonctionnelles de forme, geometriques and morphomorphizers, which are used for the analysis of images.
References
More filters
Journal ArticleDOI
Reversible jump Markov chain Monte Carlo computation and Bayesian model determination
TL;DR: In this article, the authors propose a new framework for the construction of reversible Markov chain samplers that jump between parameter subspaces of differing dimensionality, which is flexible and entirely constructive.
Journal Article
Simulation Procedures and Likelihood Inference for Spatial Point Processes
Charles J. Geyer,Jesper Møller +1 more
TL;DR: In this paper, an alternative algorithm to the usual birth-and-death procedure for simulating spatial point processes is introduced, which is used in a discussion of unconditional versus conditional likelihood inference for parametric models of spatial point process.
MonographDOI
Stochastic geometry: likelihood and computation
TL;DR: Stochastic Geometry: Likelihood and Computation provides a coordinated collection of chapters on important aspects of the rapidly developing field of stochastic geometry, including a "crash-course" introduction to key stochastics geometry themes.
Journal ArticleDOI
Bayesian object identification
Håvard Rue,Merrilee Hurn +1 more
TL;DR: In this paper, the authors combine the approaches of marked point processes and deformable template models to handle scenes containing variable numbers of objects of different types, using reversible jump Markov chain Monte Carlo methods for inference.
Journal ArticleDOI
A RJMCMC Algorithm for Object Processes in Image Processing
TL;DR: A general interacting objects model, which includes a data term and some geometrical constraints, is proposed, and a Reversible Jump Markov Chain Monte Carlo algorithm is derived to optimise the proposed model.