Julien Dardenne

Document Image Segmentation Using a 2D Conditional Random Field Model

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.

Variational tetrahedral mesh generation from discrete volume data

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.

Graph-based multi-scale analysis of plates and rods in human trabecular bone

Trabecular bone is made of a complex network of plate and rod structures, the proportion of which evolves with age or disease. Thus the identification of trabecular plates and rods is important in understanding bone fragility. We propose a novel approach based on 3D multi-scale adjacency graph analysis of high resolution 3D tomographic images of bone structures. The purpose of this new method is to classify each voxel of the 3D images in two classes: plate and rod voxels. We show that the use of a multi-scale framework is very efficient at detecting rods with different sizes. We present applications of our method to both synthetic images and experimental bone synchrotron radiation micro-CT images.

Exploiting curvature to compute the medial axis with Constrained Centroidal Voronoi Diagram on discrete data

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.