This paper introduces the neuractive pyramids to model objects under elastic deformations . One pyramid is built on each frame of the image sequence . Each level of the pyramid is a regular graph that is recursively built on a low-pass version of the original picture . Cells of this graph deform to model the local information of the picture . Deformations are obtained by the minimization of an energy function computed both on the gradient of the picture and the graph structure . Each cell contains a vector of statistical moments computed on its domain and its neighborood . Matching pyramids defines a vector Field of local elastic transformations . The matching operator is based on a self-organizing map, introduced by Kohonen . Softness...
Image registration methods, which aim at aligning two or more images into one coordinate system, are...
- Nous montrons comment un processus de segmentation peut être utilisé localement sur des régions d'...
The segmentation of abdomen organs in volumetric medical images is difficult due to noisy and low co...
This paper describes an approach to image segmentation. ne methods intended for images where local ...
Une pyramide de graphes, constituant un modèle multirésoltuion déformable est utilisée pour la recon...
Dans la méthode proposée, une pyramide irrégulière est utilisée pour segmenter les images d'une séqu...
We present a new class of hierarchical structures known as the irregular pyramid . This pyramid is ...
Moving away from constrained parametric to unconstrained flexible non parametric models is a deep tr...
This article presents a new algorithm for segmenting three-dimensional images . It is based on a dyn...
Une nouvelle approche de segmentation d'image, basée d'une part sur une architecture pyramidale et d...
In the digital world, two-dimensional (2D) and three-dimensional (3D) shapes are important for repre...
Nous traitons le problème de la convergence d'un algorithme d'estimation du mouvement pour le recala...
This thesis explores the use of discriminatively trained deformable contour models (DCMs) for shape-...
Whether in pattern recognition or machine learning, it is a common practice to define a feature spac...
Measuring displacement and strain fields at low observable scales in complex microstructures still r...
Image registration methods, which aim at aligning two or more images into one coordinate system, are...
- Nous montrons comment un processus de segmentation peut être utilisé localement sur des régions d'...
The segmentation of abdomen organs in volumetric medical images is difficult due to noisy and low co...
This paper describes an approach to image segmentation. ne methods intended for images where local ...
Une pyramide de graphes, constituant un modèle multirésoltuion déformable est utilisée pour la recon...
Dans la méthode proposée, une pyramide irrégulière est utilisée pour segmenter les images d'une séqu...
We present a new class of hierarchical structures known as the irregular pyramid . This pyramid is ...
Moving away from constrained parametric to unconstrained flexible non parametric models is a deep tr...
This article presents a new algorithm for segmenting three-dimensional images . It is based on a dyn...
Une nouvelle approche de segmentation d'image, basée d'une part sur une architecture pyramidale et d...
In the digital world, two-dimensional (2D) and three-dimensional (3D) shapes are important for repre...
Nous traitons le problème de la convergence d'un algorithme d'estimation du mouvement pour le recala...
This thesis explores the use of discriminatively trained deformable contour models (DCMs) for shape-...
Whether in pattern recognition or machine learning, it is a common practice to define a feature spac...
Measuring displacement and strain fields at low observable scales in complex microstructures still r...
Image registration methods, which aim at aligning two or more images into one coordinate system, are...
- Nous montrons comment un processus de segmentation peut être utilisé localement sur des régions d'...
The segmentation of abdomen organs in volumetric medical images is difficult due to noisy and low co...