This thesis interests in different methods of image compression combining both Bayesian aspects and “sparse decompositions” aspects. Two compression methods are in particular investigated. Transform coding, first, is addressed from a transform optimization point of view. The optimization is considered at two levels: in the spatial domain by adapting the support of the transform, and in the transform domain by selecting local bases among finite sets. The study of bases learned with an algorithm from the literature constitutes an introduction to a novel learning algorithm, which encourages the sparsity of the decompositions. Predictive coding is then addressed. Motivated by some recent contributions based on sparse decompositions, we propose ...
Sparse coding is a promising theme in computer vision. Most of the existing sparse coding methods ar...
Abstract. Images can be coded accurately using a sparse set of vectors from a learned overcomplete d...
Cette thèse étudie deux modèles paramétriques et non paramétriques pour le changement de représentat...
This thesis interests in different methods of image compression combining both Bayesian aspects and ...
Cette thèse s'intéresse à différentes techniques de compression d'image combinant à la fois des aspe...
This thesis studies three popular dimension reduction techniques: compressed sensing, random project...
Abstract—Nonparametric Bayesian methods are considered for recovery of imagery based upon compressiv...
Dans le domaine de la classification, les algorithmes d'apprentissage par compression d'échantillon...
Sparse regression methods are used for the reconstruction of compressed signals, that are usually sp...
Compressed sensing allows to reconstruct a signal from a few linear projections, under the assumptio...
This thesis is motivated by the perspective of connecting compressed sensing and machine learning, a...
La modélisation des signaux peut être vue comme la pierre angulaire de la méthodologie contemporaine...
Nowadays image compression has become a necessity due to a large volume of images. For efficient use...
This thesis covers different topics on design of image compression algorithms. The main focus in thi...
Compressed Sensing (CS) is an established way to perform efficient dimensionality reduction during a...
Sparse coding is a promising theme in computer vision. Most of the existing sparse coding methods ar...
Abstract. Images can be coded accurately using a sparse set of vectors from a learned overcomplete d...
Cette thèse étudie deux modèles paramétriques et non paramétriques pour le changement de représentat...
This thesis interests in different methods of image compression combining both Bayesian aspects and ...
Cette thèse s'intéresse à différentes techniques de compression d'image combinant à la fois des aspe...
This thesis studies three popular dimension reduction techniques: compressed sensing, random project...
Abstract—Nonparametric Bayesian methods are considered for recovery of imagery based upon compressiv...
Dans le domaine de la classification, les algorithmes d'apprentissage par compression d'échantillon...
Sparse regression methods are used for the reconstruction of compressed signals, that are usually sp...
Compressed sensing allows to reconstruct a signal from a few linear projections, under the assumptio...
This thesis is motivated by the perspective of connecting compressed sensing and machine learning, a...
La modélisation des signaux peut être vue comme la pierre angulaire de la méthodologie contemporaine...
Nowadays image compression has become a necessity due to a large volume of images. For efficient use...
This thesis covers different topics on design of image compression algorithms. The main focus in thi...
Compressed Sensing (CS) is an established way to perform efficient dimensionality reduction during a...
Sparse coding is a promising theme in computer vision. Most of the existing sparse coding methods ar...
Abstract. Images can be coded accurately using a sparse set of vectors from a learned overcomplete d...
Cette thèse étudie deux modèles paramétriques et non paramétriques pour le changement de représentat...