Abstract In this paper, we propose a novel tetrahedral mesh generation algorithm, which takes volumic data (voxels) as an input. Our algorithm performs a clustering of the original voxels within a variational framework. A vertex replaces each cluster and the set of created vertices is triangulated in order to obtain a tetrahedral mesh, taking into account both the accuracy of the representation and the elements quality. The resulting meshes exhibit good elements quality with respect to minimal dihedral angle and tetrahedra form factor. Experimental results show that the generated meshes are well suited for Finite Element Simulations.

Abstract In this paper, we propose a new method for generate anatomical meshes by tetrahedral elements with the aim of simulating the phenomena resulting from a voluntary or involuntary exposure of the human body at waves radio frequencies. This mesh will be used to resolve, by the finite element method, the equations of Maxwell, for the electromagnetic part and the equation of Pennes for thermal part. we propose a novel tetrahedral mesh generation algorithm, which takes volumic data (voxels) as an input.

Abstract In this work we are interested in image analysis thanks to the use of Markovian generative and discriminative models : Hidden Markov Random Fields and Conditional Random Fields. We present a 2D implementation of conditional random fields which have been used mainly for on dimensional data until now. The proposed approach is based on a discriminative classifiers combination scheme. We illustrate and compare the performance of this approach with Hidden Markov random fields through its application to document structure analysis of complex degraded Handwritten Documents : Flaubert's manuscripts.

Abstract : Finite element simulation can be directly affected by mesh quality. The accuracy of finite element calculations is dependent upon of the mesh quality. Previously, we have introduced a novel approach to the construction of high-quality, isotropic tetrahedral meshes from segmented medical imaging data. This article proposes an experimental evaluation of the impact of our tetrahedral meshes on electromagnetic and thermal simulations with finite elements.

Abstract : In this paper, we present a novel method for medial axis approximation based on Constrained Centroidal Voronoi Diagram of discrete data (image, volume). The proposed approach is based on the shape boundary subsampling controled by a clustering approach which generates a Voronoi Diagram well suited for Medial Axis extraction. The resulting Voronoi Diagram is further filtered in order to capture the correct topology of the medial axis. The main contribution of this paper is the integration of both a curvature maps and a distance map for controlling the local variability of Voronoi cells densities. Examples of complex shape processing prove the effectiveness of the proposed approach.

Abstract : This work relates to the implementation of a 2D conditional random field model in the context of document image analysis. Our model makes it possible to take variability into account and to integrate contextual knowledge, while taking benefit from machine learning techniques. Experiments on handwritten drafts of Flaubert show that these models provide interesting solutions.

Abstract : In this article, we consider the problem of the medial axis approximation from a discrete object (image or volume). The proposed approach is based on the shape boundary subsampling by a clustering approach which generates a Voronoi Diagram well suited for Medial Axis extraction. The resulting Voronoi Diagram is further filtered so as to capture the correct topology of the medial axis. The method is tested on various synthetic as well as real images. The resulting medial axis appears largely invariant with respect to typical noise conditions in the discrete data.

Abstract : This work relates to the implementation of a 2D conditional random field model in the context of document image analysis. Our model makes it possible to take variability into account and to integrate contextual knowledge, while taking benefit from machine learning techniques. Experiments on handwritten drafts of Flaubert show that these models provide interesting solutions.