Emmanuel Monfrini

PUBLICATIONS SCIENTIFIQUES

Revues


R18	*Pairwise Markov fields for segmentation in astronomical hypersprectral images. JB Courbot, V Mazet, E Monfrini, C Collet, Signal Processing 163, 41-48*

R17	*Oriented Triplet Markov Fields. JB Courbot, E Monfrini, V Mazet, C Collet, Pattern Recognition Letters 103, 16-22*

R16	*Assessing the segmentation performance of pairwise and triplet Markov models Signal Processing. I Gorynin, H Gangloff, E Monfrini and W Pieczynski, Signal Processing 145, 183-192.*

R15	*A framework based on hidden Markov trees for multimodal PET/CT image co-segmentation. H Hanzouli-Ben Salah, J Lapuyade-Lahorgue, D Benoit, J Bert, P Lambin, A Van Baardwijk, E Monfrini, W Pieczynski, D Visvikis, M Hatt, Med Phys. 2017 Aug 24. doi: 10.1002/mp.12531*

R14	*Extended faint source detection in astronomical hyperspectral images. JB Courbot, V Mazet, E Monfrini, C Collet, Signal Processing 135, 274-283*

R13	*Fast smoothing in switching approximations of non-linear and non-Gaussian models. I Gorynin, S Derrode, E Monfrini, W Pieczynski, Computational Statistics & Data Analysis Volume 114, October 2017, Pages 38–46*

R12	*Fast Filtering in Switching Approximations of Nonlinear Markov Systems With Applications to Stochastic Volatility. I Gorynin, S Derrode, E Monfrini, W Pieczynski, IEEE Transactions on Automatic Control 62 (2), 853-862*

R11	*Markov Chains for unsupervised segmentation of degraded NIR iris images for person recognition. M Yahiaoui, E Monfrini, B Dorizzi, Pattern Recognition Letters 82, 116-123*

R10	*Vertebra segmentation based on two-step refinement. JB Courbot, E Rust, E Monfrini, C Collet, Journal of Computational Surgery 4 (1), 1*

R9	*Performance comparison across hidden, pairwise and triplet Markov models’ estimators. I Gorynin, L Crelier, H Gangloff, E Monfrini, W Pieczynski, International journal of mathematical and computational methods (IJMCM) 1, 253-258.*

R8	*Optimal filtering in hidden and pairwise Gaussian Markov systems. I Gorynin, E Azeraf, W Sabbagh, E Monfrini, W Pieczynski, International journal of mathematical and computational methods (IJMCM) 1, 259-263*

R7	*Phasic triplet Markov chains. MEY Boudaren, E Monfrini, W Pieczynski, A Aissani, IEEE transactions on pattern analysis and machine intelligence 36 (11), 2310*

R6	*Dempster–Shafer fusion of multisensor signals in nonstationary Markovian context. MEY Boudaren, E Monfrini, W Pieczynski, A Aïssani, EURASIP Journal on Advances in Signal Processing 2012 (1), 134*

R5	*Unsupervised segmentation of random discrete data hidden with switching noise distributions. MEY Boudaren, E Monfrini, W Pieczynski, IEEE Signal Processing Letters 19 (10), 619-622*

R4	*A quadratic loss multi-class SVM for which a radius–margin bound applies. Y Guermeur, E Monfrini, Informatica 22 (1), 73-96*

R3	*Generalized mixture estimation in hidden Markov trees, application to segmentation of images of street organ cards. E Monfrini, W Pieczynski, Traitement du Signal 22 (2), 135-148*

R2	*Une méthode des moments stable pour les mélanges de deux distributions normales. E Monfrini, Revue Roumaine de Mathématiques Pures et Appliquées 49 (1), 45-62*

R1	*Unicité dans la méthode des moments pour les mélanges de deux distributions normales. E Monfrini, Comptes Rendus Mathématiques de l’Académie des Sciences 336 (1), 89-94*

Conférences


C32	*Segmentation de stents dans des données médicales à rayons-X corrompues par les artéfacts. H Gangloff, E Monfrini, C Collet, N Chakfé, Colloque GRETSI 2019*

C31	*Segmentation non-supervisée dans les champs de Markov Couple gaussiens. H Gangloff, JB Courbot, E Monfrini, C Collet , Colloque GRETSI 2019*

C30	*Triplet Markov trees for image segmentation. JB Courbot, E Monfrini, V Mazet, C Collet, 2018 IEEE Statistical Signal Processing Workshop (SSP), 233-237*

C29	*Arbres de Markov triplets pour la segmentation d'image. JB Courbot, E Monfrini, V Mazet, C Collet, GRETSI 2017*

C28	*Estimation de la variance stochastique multivariée avec un filtre gaussien basé sur la méthode de Laplace. I Gorynin, E Monfrini, W Pieczynski, GRETSI 2017*

C27	*Pairwise Markov Models for Stock Index Forecasting. I Gorynin, E Monfrini, W Pieczynski, 2017 25th European Signal Processing Conference (EUSIPCO), 2041-2045*

C26	*Unsupervised Segmentation of Nonstationary Data using Triplet Markov Chains. MEY Boudaren , E Monfrini , K Beghdad Bey , A Habbouchi, W Pieczynski, Proceedings of the 19th International Conference on Enterprise Information Systems - Volume 1: ICEIS, 405-414, 2017, Porto, Portugal*

C25	*Unsupervised learning of Markov-switching stochastic volatility with an application to market data. I Gorynin, E Monfrini, W Pieczynski, Machine Learning for Signal Processing (MLSP), 2016 IEEE 26th International ...*

C24	*Oriented Triplet Markov Field for Hyperspectral Image Segmentation. JB Courbot, E Monfrini, V Mazet, C Collet, IEEE Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, Aug 2016, Los Angeles, United States.*

C23	*Fast filtering with new sparse transition markov chains. I Gorynin, E Monfrini, W Pieczynski, Statistical Signal Processing Workshop (SSP), 2016 IEEE, 1-5*

C22	*Detection of faint extended sources in hyperspectral data and application to HDF-S MUSE observations. JB Courbot, V Mazet, E Monfrini, C Collet, Acoustics, Speech and Signal Processing (ICASSP), 2016*

C21	*2-Step robust vertebra segmentation. JB Courbot, E Rust, E Monfrini, C Collet, Image Processing Theory, Tools and Applications (IPTA), 2015*

C20	*Segmentation robuste de vertèbres. JB Courbot, E Rust, E Monfrini, C Collet, GRETSI'2015*

C19	*Lissage rapide dans des modèles non linéaires et non gaussiens. I Gorynin, S Derrode, E Monfrini, W Pieczynski, GRETSI'2015*

C18	*Exact fast smoothing in switching models with application to stochastic volatility. I Gorynin, S Derrode, E Monfrini, W Pieczynski, Signal Processing Conference (EUSIPCO), 2015 23rd European, 924-928*

C17	*Implementation of unsupervised statistical methods for low-quality iris segmentation. M Yahiaoui, E Monfrini, B Dorizzi, Signal-Image Technology and Internet-Based Systems (SITIS), 2014*

C16	*PET/CT image denoising and segmentation based on a multi observation and a multi scale Markov tree model. H Hanzouli, J Lapuyade-Lahorgue, E Monfrini, G Delso, W Pieczynski, Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC), 2013*

C15	*Poursuite de cible par un senseur mobile; Repérage multisenseur de la position du senseur mobile. M Blanc-Patin, M Chevalier, A Dupont, E Monfrini, Y Petetin, Gretsi 2013*

C14	*Unsupervised segmentation of nonstationary pairwise Markov chains using evidential priors. MEY Boudaren, E Monfrini, W Pieczynski, Signal Processing Conference (EUSIPCO), 2012*

C13	*Filtrage particulaire optimal et filtrage particulaire auxiliaire adapté: Une analyse non asymptotique. F Desbouvries, Y Petetin, E Monfrini, GRETSI 2011*

C12	*Arbres de Markov couple et segmentation non supervisée d’images: cas de la mono-résolution. E Monfrini, W Pieczynski, GRETSI 2011*

C11	*Unsupervised segmentation of switching pairwise Markov chains. MEY Boudaren, E Monfrini, W Pieczynski, Image and Signal Processing and Analysis (ISPA), 2011*

C10	*Switching pairwise Markov chains for non stationary textured images segmentation. MEY Boudaren, E Monfrini, W Pieczynski, Proceedings of IADIS Int. Conf. Computer Graphics, Visualization, Computer ...*

C9	*A non asymptotical analysis of the optimal sir algorithm vs. the fully adapted auxiliary particle filter. F Desbouvries, Y Petetin, E Monfrini, Statistical Signal Processing Workshop (SSP), 2011 IEEE, 213-216*

C8	*Optimal SIR algorithm vs. fully adapted auxiliary particle filter: a matter of conditional independence. F Desbouvries, Y Petetin, E Monfrini, Acoustics, Speech and Signal Processing (ICASSP), 2011*

C7	*Unsupervised segmentation of non stationary data hidden with non stationary noise. MEY Boudaren, W Pieczynski, E Monfrini, Systems, Signal Processing and their Applications (WOSSPA), 2011*

C6	*Radius-margin bound on the leave-one-out error of the LLW-M-SVM. Y Guermeur, E Monfrini, ASMDA 2009: XIII International Conference Applied Stochastic Models and Data Analysis*

C5	*Borne" rayon-marge" sur l'erreur" leave-one-out" des SVM multi-classes. Y Darcy, E Monfrini, Y Guermeur, JDS 2006*

C4	*Estimation de mélanges généralisés dans les arbres de Markov cachés, application à la segmentation des images de cartons d'orgue de barbarie. E Monfrini, W Pieczynski, GRETSI 2005*

C3	*Image and signal restoration using pairwise Markov trees. E Monfrini, J Lecomte, F Desbouvries, W Pieczynski, Statistical Signal Processing, 2003 IEEE Workshop on, 174-177*

C2	*Segmentation non supervisée des images par arbres de Markov couple. E Monfrini, W Pieczynski, GRETSI 2003*

C1	*Segmentation non supervisée d'images par arbres de Markov cachés. E Monfrini, T Ledru, E Vaie, W Pieczynski, GRETSI 1999*

Rapports de Recherches


RR2	*A quadratic loss multi-class SVM. E Monfrini, Y Guermeur, RR - arXiv preprint arXiv:0804.4898*

RR1	*Radius-margin Bound on the Leave-one-out Error of Multi-class SVMs. Y Darcy, Y Guermeur, E Monfrini, no RR-5780, INRIA, 2005*

Thèse de doctorat


Thèse de doctorat	Identifiabilité et méthode des moments dans les mélanges généralisés de distributions du système de Pearson. (Tome1)(Tome2) La thèse a été codirigée par Mr D. Pierre-Loti-Viaud et Mr W. Pieczynski et soutenue le 04/01/02 devant le jury présidé par Mr M.Yor et composé de Mr M. Broniatovski, P. Deheuvels, A. Hillion et C. Robert. Financés par une allocation MENRT, les travaux de recherches ont été effectués dans le cadre dune collaboration entre le LSTA (Université Paris 6) et le département CITI de lInstitut National des Télécommunications dEvry. Il sagit dune étude théorique des mélanges finis généralisés complétée par des applications à la segmentation statistique des images.