WorldCat Identities

Zerubia, Josiane 1957-

Overview
Works: 67 works in 160 publications in 2 languages and 1,218 library holdings
Genres: Conference papers and proceedings 
Roles: Editor, Thesis advisor, Author, htt, Other, Opponent, Contributor
Classifications: TA1634, 006.37
Publication Timeline
.
Most widely held works by Josiane Zerubia
Energy minimization methods in computer vision and pattern recognition : 4th international workshop, EMMCVPR 2003, Lisbon, Portugal, July 7-9, 2003 : proceedings by Anand Rangarajan( )

14 editions published in 2003 in English and held by 380 WorldCat member libraries worldwide

This book constitutes the refereed proceedings of the 4th International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition, EMMCVPR 2003, held in Lisbon, Portugal in July 2003. The 33 revised full papers presented were carefully reviewed and selected from 66 submissions. The papers are organized in topical sections on unsupervised learning and matching, probabilistic modeling, segmentation and grouping, shape modeling, restoration and reconstruction, and graphs and graph-based methods
Energy minimization methods in computer vision and pattern recognition : Third International Workshop, EMMCVPR 2001, Sophia Antipolis, France, September 3-5, 2001 : proceedings by Mário Figueiredo( )

13 editions published in 2001 in English and held by 378 WorldCat member libraries worldwide

This volume consists of the 42 papers presented at the International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR2001),whichwasheldatINRIA(InstitutNationaldeRechercheen Informatique et en Automatique) in Sophia Antipolis, France, from September 3 through September 5, 2001. This workshop is the third of a series, which was started with EMMCVPR'97, held in Venice in May 1997, and continued with EMMCVR'99, which took place in York, in July 1999. Minimization problems and optimization methods permeate computer vision (CV), pattern recognition (PR), and many other ?elds of machine intelligence. The aim of the EMMCVPR workshops is to bring together people with research interests in this interdisciplinary topic. Although the subject is traditionally well represented at major international conferences on CV and PR, the EMMCVPR workshops provide a forum where researchers can report their recent work and engage in more informal discussions. We received 70 submissions from 23 countries, which were reviewed by the members of the program committee. Based on the reviews, 24 papers were - cepted for oral presentation and 18 for poster presentation. In this volume, no distinction is made between papers that were presented orally or as posters. The book is organized into ?ve sections, whose topics coincide with the ?ve s- sionsoftheworkshop:"ProbabilisticModelsandEstimation","ImageModelling and Synthesis", "Clustering, Grouping, and Segmentation", "Optimization and Graphs", and "Shapes, Curves, Surfaces, and Templates"
Mathematical models for remote sensing image processing : models and methods for the analysis of 2D satellite and aerial images( )

14 editions published between 2017 and 2018 in English and held by 206 WorldCat member libraries worldwide

This book maximizes reader insights into the field of mathematical models and methods for the processing of two-dimensional remote sensing images. It presents a broad analysis of the field, encompassing passive and active sensors, hyperspectral images, synthetic aperture radar (SAR), interferometric SAR, and polarimetric SAR data. At the same time, it addresses highly topical subjects involving remote sensing data types (e.g., very high-resolution images, multiangular or multiresolution data, and satellite image time series) and analysis methodologies (e.g., probabilistic graphical models, hierarchical image representations, kernel machines, data fusion, and compressive sensing) that currently have primary importance in the field of mathematical modelling for remote sensing and image processing. Each chapter focuses on a particular type of remote sensing data and/or on a specific methodological area, presenting both a thorough analysis of the previous literature and a methodological and experimental discussion of at least two advanced mathematical methods for information extraction from remote sensing data. This organization ensures that both tutorial information and advanced subjects are covered. With each chapter being written by research scientists from (at least) two different institutions, it offers multiple professional experiences and perspectives on each subject. The book also provides expert analysis and commentary from leading remote sensing and image processing researchers, many of whom serve on the editorial boards of prestigious international journals in these fields, and are actively involved in international scientific societies. Providing the reader with a comprehensive picture of the overall advances and the current cutting-edge developments in the field of mathematical models for remote sensing image analysis, this book is ideal as both a reference resource and a textbook for graduate and doctoral students as well as for remote sensing scientists and practitioners
Markov random fields in image segmentation by Zoltan Kato( )

9 editions published between 2011 and 2014 in English and held by 51 WorldCat member libraries worldwide

This monograph gives an introduction to the fundamentals of Markovian modeling in image segmentation as well as a brief overview of recent advances in the field. Segmentation is considered in a common framework, called image labeling, where the problem is reduced to assigning labels to pixels. In a probabilistic approach, label dependencies are modeled by Markov random fields (MRF) and an optimal labeling is determined by Bayesian estimation, in particular maximum a posteriori (MAP) estimation. The main advantage of MRF models is that prior information can be imposed locally through clique potentials. The primary goal is to demonstrate the basic steps to construct an easily applicable MRF segmentation model and further develop its multiscale and hierarchical implementations as well as their combination in a multilayer model. MRF models usually yield a non-convex energy function. The minimization of this function is crucial in order to find the most likely segmentation according to the MRF model. Besides classical optimization algorithms, like simulated annealing or deterministic relaxation, we also present recently introduced graph cut-based algorithms. We briefly discuss the possible parallelization techniques of simulated annealing, which allows efficient implementation on, e.g., GPU hardware without compromising convergence properties of the algorithms. While the main focus of this monograph is on generic model construction and related energy minimization methods, many sample applications are also presented to demonstrate the applicability of these models in real life problems such as remote sensing, biomedical imaging, change detection, and color- and motion-based segmentation. In real-life applications, parameter estimation is an important issue when implementing completely data-driven algorithms. Therefore some basic procedures, such as expectation-maximization, are also presented in the context of color image segmentation
Energy Minimization Methods in Computer Vision and Pattern Recognition : 4th International Workshop, EMMCVPR 2003, Lisbon, Portugal, July 7-9, 2003. Proceedings by Anand Rangarajan( )

1 edition published in 2003 in English and held by 32 WorldCat member libraries worldwide

Mean field annealing using compound Gauss-Markov random fields for edge detection and image restoration by Josiane Zerubia( Book )

2 editions published in 1990 in English and held by 7 WorldCat member libraries worldwide

We emphasize on the need of an optimal step-descent method to get a robust algorithm. Lastly, we present edge detection and image restoration results on a noisy aerial image (SNR = 5 dB) with line-process interaction and compare them with those obtained without such an interaction."
Image segmentation using 4 direction line-processes = Segmentation d'image utilisant des processus de ligne dans 4 directions by Josiane Zerubia( Book )

4 editions published in 1990 in English and held by 6 WorldCat member libraries worldwide

Furthermore, we show how we propagate the lines at low temperatures including an additional constraint in the cost (or energy) function. Then, we present simulation results obtained on real images with a connection machine CM2 using an optimal step descent technique to minimize the cost. We compare these results to those obtained with an algorithm previously proposed and which only deals with horizontal and vertical line-processes."
Classical mechanics and roads detection in spot images = Mecanique classique et detection de routes dans les images spot by Institut National de Recherche en Informatique et en Automatique( Book )

3 editions published in 1993 in English and held by 5 WorldCat member libraries worldwide

Abstract: "The detection of roads in satellite images has drawn a lot of attention in the last ten years. Problems of resolution, noise, and image understanding are involved, and one of the best method [sic] developed so far is the F* algorithm of Fischler, which is based on dynamic programming. We present herein a mathematical formalization of the F*, an extension to cliques of higher order to deal with the contrast, an extension to neighborhoods of higher order to take into account the curvature, and a physical dynamic model to use the curvature information in a more natural and global way."
Image classification using Markov random fields with two new relaxation methods : deterministic pseudo annealing and modified metropolis dynamics = Classification d'image à l'aide des champs de Markov avec deux nouvelles méthodes de relaxation : pseudo-recuit déterministe et dynamique de metropolis modifiée by Zoltan Kato( Book )

4 editions published in 1992 in English and held by 5 WorldCat member libraries worldwide

Abstract: "In this paper, we present two relaxation techniques: Deterministic Pseudo-Annealing (DPA) and Modified Metropolis Dynamics (MMD) in order to do image classification using a Markov Random Field modelization. For the first algorithm (DPA), the a posteriori probability of a tentative labeling is generalized to continuous labeling. The merit function thus defined has the same maxima under constraints yielding probability vectors. Changing these constraints convexify the merit function. The algorithm solve [sic] this unambiguous maximization problem and then tracks down the solution while the original constraints are restored yielding a good even if suboptimal solution to the original labeling assignment problem. As for the second method (MMD), it is a modified version of the Metropolis algorithm: at each iteration the new state is chosen randomly but the decision to accept it is purely deterministic. This is of course also a suboptimal technique which gives faster results than stochastic relaxation. These two methods have been implemented on a Connection Machine CM2 and simulation results are shown with a synthetic noisy image and a SPOT image. These results are compared to those obtained with the Metropolis algorithm, the Gibbs sampler and ICM (Iterated Conditional Mode)."
ANALYSE DE TEXTURE PAR METHODES MARKOVIENNES ET PAR MORPHOLOGIE MATHEMATIQUE : APPLICATION A L'ANALYSE DES ZONES URBAINES SUR DES IMAGES SATELLITALES by ANNE LORETTE( Book )

2 editions published in 1999 in French and held by 5 WorldCat member libraries worldwide

DANS CETTE THESE, NOUS NOUS INTERESSONS AU PROBLEME DE L'ANALYSE URBAINE A PARTIR D'IMAGES SATELLITALES PAR DES METHODES AUTOMATIQUES OU SEMI-AUTOMATIQUES ISSUES DU TRAITEMENT D'IMAGE. DANS LE PREMIER CHAPITRE, NOUS PRESENTONS LE CONTEXTE DANS LEQUEL LE TRAVAIL A ETE EFFECTUE. NOUS EXPOSONS LES TYPES DE DONNEES UTILISEES, LES APPROCHES STATISTIQUES CONSIDEREES. NOUS DONNONS EGALEMENT QUELQUES EXEMPLES D'APPLICATIONS QUI JUSTIFIENT UNE TELLE ETUDE. ENFIN, UN ETAT DE L'ART DES DIVERSES METHODES D'ANALYSE DES TEXTURES EST PRESENTE. DANS LES DEUX CHAPITRES SUIVANTS, NOUS DEVELOPPONS UNE METHODE AUTOMATIQUE D'EXTRACTION D'UN MASQUE URBAIN A PARTIR D'UNE ANALYSE DE LA TEXTURE DE L'IMAGE. DES METHODES D'EXTRACTION D'UN MASQUE URBAIN SONT DECRITES. ENSUITE, NOUS DEFINISSONS PLUS PRECISEMMENT LES HUIT MODELES MARKOVIENS GAUSSIENS FONDES SUR DES CHAINES. CES MODELES SONT RENORMALISES PAR UNE METHODE DE RENORMALISATION DE GROUPE ISSUE DE LA PHYSIQUE STATISTIQUE AFIN DE CORRIGER LE BIAIS INTRODUIT PAR L'ANISOTROPIE DU RESEAU DE PIXELS. L'ANALYSE DE TEXTURE PROPOSEE EST COMPAREE AVEC DEUX METHODES CLASSIQUES : LES MATRICES DE COOCCURRENCE ET LES FILTRES DE GABOR. L'IMAGE DU PARAMETRE DE TEXTURE EST ENSUITE CLASSIFIEE AVEC UN ALGORITHME NON SUPERVISE DE CLASSIFICATION FLOUE FONDEE SUR LA DEFINITION D'UN CRITERE ENTROPIQUE. LES PARAMETRES ESTIMES AVEC CET ALGORITHME SONT INTEGRES DANS UN MODELE MARKOVIEN DE SEGMENTATION. DES RESULTATS D'EXTRACTION DE MASQUES URBAINS SONT FINALEMENT PRESENTES SUR DES IMAGES SATELLITALES OPTIQUES SPOT3, DES SIMULATIONS SPOT5, ET DES IMAGES RADAR ERS1. DANS LE QUATRIEME CHAPITRE, NOUS PRESENTONS L'ANALYSE GRANULOMETRIQUE UTILISEE POUR ANALYSER LE PAYSAGE URBAIN. LES OUTILS ET DEFINITIONS DE BASE DE LA MORPHOLOGIE MATHEMATIQUE SONT EXPOSES. NOUS NOUS INTERESSONS PLUS PARTICULIEREMENT A L'OUVERTURE PAR RECONSTRUCTION QUI EST UTILISEE COMME TRANSFORMATION DE BASE DE LA GRANULOMETRIE. L'ETAPE DE QUANTIFICATION QUI SUIT TOUT ETAPE DE TRANSFORMATION NOUS PERMET D'ESTIMER EN CHAQUE PIXEL UNE DISTRIBUTION LOCALE DE TAILLE QUI EST INTEGREE DANS LE TERME D'ATTACHE AUX DONNEES D'UN MODELE MARKOVIEN DE SEGMENTATION. DES TESTS SONT EFFECTUES SUR DES SIMULATIONS SPOT5
Detection de contours et restauration d'image par des algorithmes deterministes de relaxation : mise en oeuvre sur la machine a connexions CM2 = Edge detection and image restoration using two deterministic relaxation algorithms : implementation on the connection machine CM2 by Josiane Zerubia( Book )

1 edition published in 1990 in French and held by 4 WorldCat member libraries worldwide

In this report, we focus on the parallel implementation of two deterministic algorithms for edge detection and image restoration: the graduated non-convexity (GNC) originally proposed by Blake & Zisserman and the mean field annealing (MFA) introduced by Geiger & Girosi and extended to anisotropic compound Gauss-Markov random fields by Zerubia & Chellappa. Both methods are based on a weak-membrane model and both algorithms are inherently serial: each step produces a pixel map which is taken as an input for the next step. For the GNC, we implement a checkerboard version of the successive over-relaxation (SOR) method to minimize the energy. For the MFA, we use an optimal step conjugate gradient descent."
Processus ponctuels marqués pour l'extraction automatique de caricatures de bâtiments à partir de modèles numériques d'élévation by Mathias Ortner( Book )

2 editions published in 2004 in French and held by 4 WorldCat member libraries worldwide

The context of this thesis is the reconstruction of urban areas from images. It proposes a set of algorithms for extracting simple shapes from Digital Elevation Models (DEM). DEMs describe the altimetry of an urban area by a grid of points, each of which has a height associated to it. The proposed models are based on marked point processes. These mathematical objects are random variables whose realizations are configurations of geometrical shapes. Using these processes, we can introduce constraints on the shape of the objects to be detected in an image, and a regularizing term incorporating geometrical interactions between objects. An energy can be associated to each object configuration, and the global minima of this energy can then be found by applying simulated annealing to a Reversible Jump Monte Carlo Markov Chain sampler (RJMCMC). We propose four different models for extracting the outlines of buildings from altimetric descriptions of dense urban areas. Each of these models is constructed from an object shape, a data energy, and a regularizing energy. The first two models extract simple shapes (rectangles) using, respectively, a homogeneity constraint and discontinuity detection. The third model looks for three-dimensional polyhedral buildings. The last model uses cooperation between two types of objects, rectangles and segments. The resulting algorithms are evaluated on real data provided by the French National Geographic Institute (a laser DEM and optical DEMs of differing quality)
A hierarchical Markov Random Field model and multi-temperature annealing for parallel image classification by Zoltan Kato( Book )

3 editions published in 1993 in English and held by 4 WorldCat member libraries worldwide

Restauration d'image de contours incomplets par modelisation par champs de Markov by Sabine Urago( Book )

2 editions published in 1992 in French and held by 4 WorldCat member libraries worldwide

Abstract: "In this paper, we describe an algorithm which allows the restoration of images with incomplete contours. We use Markov random fields and Gibbs distributions. In order to restore the contours, we define a few criterions which have to be optimized. Deterministic (Iterated Conditional Mode) or stochastic relaxation (Gibbs sampler) algorithms generate a configuration in which the contours are completed. Our study shows how to modify and extend the method proposed by J.L Marroquin in 1989 to enable the processing of real and noisy images. To illustrate this algorithm, several examples are given including synthetic, noisy and real (indoors and satellite : SPOT) images."
Analyse de textures dans l'espace hyperspectral par des méthodes probabilistes by Guillaume Rellier( Book )

2 editions published in 2002 in French and held by 4 WorldCat member libraries worldwide

In this work, we investigate the problem of texture analysis of urban areas. Texture is a spatial concept that refers to the visual homogeneity characteristics of an image. The aim of this research is to define a joint specctral and spatial texture model for hyperspectral images which have a large number of bands. Textures are modeled by a vectorial Gauss-Markov random field. This field has been adapted to hyperspectral images by a simplification which avoids statistical estimation problems common to high dimensional spaces. We also reduce the dimensionality of the data, using a projection pursuit algorithm, which determines a projection subspace in which a projection index is optimized. This texture analysis method is tested within a supervised classification framework, using two classification algorithms we apply to AVIRIS hyperspectral images
Contribution à la classification d'images satellitaires par approche variationnelle et équations aux dérivées partielles by Christophe Samson( Book )

2 editions published between 2000 and 2006 in French and held by 4 WorldCat member libraries worldwide

Ce travail est consacré au développement ainsi qu'à l'implantation de deux modèles variationnels pour la classification d'images. La classification d'images, consistant à attribuer une étiquette à chaque pixel d'une image, concerne de nombreuses applications à partir du moment où cette opération intervient très souvent à la base des chaînes de traitement et d'interprétation d'images. De nombreux modèles de classification ont déjà été développés dans un cadre stochastique ou à travers des approches structurales, mais rarement dans un contexte variationnel qui a déjà montré son efficacité dans divers domaines tels que la reconstruction ou la restauration d'images.Le premier modèle que nous proposons repose sur la minimisation d'une famille de critères dont la suite de solutions converge vers une partition des données composée de classes homogènes séparées par des contours réguliers. Cette approche entre dans le cadre des problèmes à discontinuité libre et fait appel à des notions de convergence variationnelle telle que la théorie de la [Gamma-]convergence. (...) Parallèlement à cette approche, nous avons développé un second modèle de classification mettant en jeu un ensemble de régions et contours actifs. Nous utilisons une approche par ensembles de niveaux pour définir le critère à minimiser, cette approche ayant déjà suscité de nombreux travaux dans le cadre de la segmentation d'images. (...) Nous avons mené des expériences sur de nombreuses données synthétiques ainsi que sur des images satellitaires SPOT. Nous avons également étendu ces deux modèles au cas de données multispectrales et obtenu des résultats sur des données SPOT XS (...)
Local edge grouping by simple process iteration by Frank Mangin( Book )

5 editions published between 1991 and 1992 in English and held by 4 WorldCat member libraries worldwide

Abstract: "A new iterative algorithm for edge intensity images enhancement is proposed. It uses local cooperation-inhibition processes to produce an edge image in which the most relevant contours have reached maximal activation, and small gaps and junctions have been filled in. Implementation on a massively parallel machine provided high speed performances, and results of experimentations with images of real scenes are presented. The algorithm is robust in complex edge images context, and is perfectly stable under any number of iterations."
Contours actifs d'ordre supérieur et leur application à la détection de linéiques dans les images de télédétection by Marie Rochery( Book )

2 editions published in 2005 in French and held by 3 WorldCat member libraries worldwide

Cette thèse aborde le problème de l'introduction d'une connaissance a priori sur la géométrie de l'objet à détecter dans le cadre général de la reconnaissance de formes dans une image. L'application choisie pour illustrer ce problème est la détection de réseaux de linéiques dans des images satellitaires et aériennes. Nous nous plaçons dans le cadre des contours actifs, qui ont été largement utilisés en traitement d'image pour l'extraction d'objets, et nous introduisons une nouvelle classe de contours actifs d'ordre supérieur. Cette classe permet la création de nouveaux modèles rendant possible l'incorporation d'informations géométriques fortes définissant plutôt qu'une forme spécifique, une famille générale de formes. Nous étudions, dans un premier temps, un cas particulier d'énergie quadratique qui favorise des structures à plusieurs bras de largeur à peu près constante et connectés entre eux. Cette énergie démontre les perspectives de modélisation qu'offre la nouvelles classe de contours actifs introduite. L'énergie étudiée ainsi que des termes linéaires de longueur et d'aire sont utilisés comme termes d'a priori pour les modèles d'extraction de linéiques que nous proposons. Plusieurs termes d'attache aux données sont proposés dont un terme quadratique permettant de lier la géométrie du contour et les propriétés de l'image. Un modèle d'extraction permettant de gérer les occultations est également présenté. Pour permettre la minimisation de l'énergie, nous développons un cadre méthodologique utilisant les courbes de niveau. Les forces non locales sont calculées sur le contour extrait avant d'être étendues sur tout le domaine considéré. Finalement, afin de résoudre certaines difficultés rencontrées avec les contours actifs standards ainsi que les nouveaux modèles, nous proposons d'utiliser des modèles de champs de phase pour modéliser les régions. Cette méthodologie offre une alternative avantageuse aux techniques classiques et nous définissons des modèles d'extraction de linéiques similaires aux contours actifs d'ordre supérieur dans ce cadre. La pertinence de tous les modèles proposés est illustrée sur des images satellitaires et aériennes réelles
La représentation et le traitement de signaux bruités by Josiane Zerubia( Book )

3 editions published in 1988 in French and held by 3 WorldCat member libraries worldwide

 
moreShow More Titles
fewerShow Fewer Titles
Audience Level
0
Audience Level
1
  General Special  
Audience level: 0.00 (from 0.00 for Energy min ... to 0.00 for Energy min ...)

Energy minimization methods in computer vision and pattern recognition : 4th international workshop, EMMCVPR 2003, Lisbon, Portugal, July 7-9, 2003 : proceedings
Covers
Energy minimization methods in computer vision and pattern recognition : Third International Workshop, EMMCVPR 2001, Sophia Antipolis, France, September 3-5, 2001 : proceedingsMathematical models for remote sensing image processing : models and methods for the analysis of 2D satellite and aerial imagesMarkov random fields in image segmentation
Alternative Names
Josiane Zerubia informática teórica francesa

Josiane Zerubia scientist at INRIA

Languages
English (73)

French (16)