l’École nationale supérieure des mines de Paris
نویسندگان
چکیده
This thesis contributes to the field of mathematical morphology and illustrates how multivariate statistics and machine learning techniques can be exploited to design vector ordering and to include results of morphological operators in the pipeline of multivariate image analysis. In particular, we make use of supervised learning, random projections, tensor representations and conditional transformations to design new kinds of multivariate ordering, and morphological filters for color and multi/hyperspectral images. Our key contributions include the following points: • Exploration and analysis of supervised ordering based on kernel methods. • Proposition of an unsupervised ordering based on statistical depth function computed by random projections. We begin by exploring the properties that an image requires to ensure that the ordering and the associated morphological operators can be interpreted in a similar way than in the case of grey scale images. This will lead us to the notion of background/foreground decomposition. Additionally, invariance properties are analyzed and theoretical convergence is showed. • Analysis of supervised ordering in morphological template matching problems, which corresponds to the extension of hit-or-miss operator to multivariate image by using supervised ordering. • Discussion of various strategies for morphological image decomposition, specifically, the additive morphological decomposition is introduced as an alternative for the analysis of remote sensing multivariate images, in particular for the task of dimensionality reduction and supervised classification of hyperspectral remote sensing images. • Proposition of an unified framework based on morphological operators for contrast enhancement and salt-and-pepper denoising. • Introduces a new framework of multivariate Boolean models using a complete lattice formulation. This theoretical contribution is useful for characterizing and simulation of multivariate textures. 7 pa st el -0 08 20 58 1, v er si on 1 6 M ay 2 01 3
منابع مشابه
École Doctorale N L'école Nationale Supérieure Des Mines De Paris Spécialité « Sciences Et Génie Des Matériaux » Présentée Et Soutenue Publiquement Par Contribution to the Development of Ideal-cell, a New Concept of Intermediate Temperature Fuel Cell
Jury Christian GUIZARD, Directeur de recherche, Laboratoire de Synthèse et Fonctionnalisation des Céramiques, Saint-Gobain/CNRS Président du jury Rose-Noëlle VANNIER, Professeur, Ecole Nationale Supérieure de Chimie de Lille Rapporteur Fabrice MAUVY, Professeur, Université de Bordeaux Rapporteur Daria VLADIKOVA, Professeur, Bulgaria Academy of Sciences Examinateur Dominique JEULIN, Directeur de...
متن کاملThèse présentée pour obtenir le grade de Docteur de l’École Nationale Supérieure des Télécommunications Spécialité: Électronique
متن کامل
Gender Differences in Hospital Mortality and Use of Percutaneous Coronary Intervention in Acute Myocardial Infarction
From PSE Paris-Jourdan Sciences Economiques (L'École des Hautes Études en Sciences Sociales – École Normale Supérieure – École Nationale des Ponts et Chaussées – Centre National de la Recherche Scientifique), Paris, France (C.M.); University of Paris-Dauphine, France, and the Institute of Health Economics and Management, Lausanne, Switzerland (B.D.); AP-HP, Henri Mondor Hospital, Department of ...
متن کاملAccurate characterization of pure silicon - substituted hydroxyapatite powders 1 synthesized by a new precipitation route 2
Accurate characterization of pure silicon-substituted hydroxyapatite powders 1 synthesized by a new precipitation route 2 David MARCHAT, Maria ZYMELKA, Cristina COELHO, Laurent GREMILLARD, 3 Lucile JOLY-POTTUZ, Florence BABONNEAU, Claude ESNOUF, Jérôme 4 CHEVALIER, Didier BERNACHE-ASSOLLANT 5 1 Ecole Nationale Supérieure des Mines, CIS-EMSE, CNRS:FRE3312, F-42023 158 cours 6 Fauriel Saint-Etien...
متن کاملThe Desirability Optimization Methodology; a Tool to Predict Two Antagonist Responses in Biotechnological Systems: Case of Biomass Growth and Hyoscyamine Content in Elicited Datura starmonium Hairy Roots
Background: The use of the desirability function approach combined with the response surface methodology (RSM), also called Desirability Optimization Methodology (DOM), has been successfully applied to solve medical, chemical, and technological questions. It is particularly effi cient for the determination of the optimal conditions in natural or industrial processes involving d...
متن کاملInertial effects on Saffman–Taylor viscous fingering
By CHRISTOPHE CHEVALIER, MARTINE BEN AMAR, DANIEL BONN AND ANKE LINDNER Laboratoire de Physique et Mécanique des Milieux Hétérogènes, UMR 7636 CNRS, Université Paris 6, Ecole Supérieure de Physique et de Chimie Industrielles, 10 rue Vauquelin, 75231 Paris cedex 05, France Laboratoire de Physique Statistique, UMR 8550 CNRS, Ecole Normale Supérieure, 24 rue Lhomond, 75231 Paris cedex 05, France E...
متن کامل