A5064845600- Medical Image Segmentation Techniques
- Topological and Geometric Data Analysis
- Image Retrieval and Classification Techniques
- 3D Surveying and Cultural Heritage
- Conservation Techniques and Studies
- Infrastructure Maintenance and Monitoring
- Remote-Sensing Image Classification
- Advanced Image and Video Retrieval Techniques
- Mathematical Biology Tumor Growth
- Advanced Numerical Analysis Techniques
- AI in cancer detection
- Advanced Mathematical Modeling in Engineering
- Computer Graphics and Visualization Techniques
- Advanced Image Fusion Techniques
- Complex Network Analysis Techniques
- 3D Shape Modeling and Analysis
- Face and Expression Recognition
- Digital Image Processing Techniques
- Nonlinear Partial Differential Equations
- Face recognition and analysis
- Millimeter-Wave Propagation and Modeling
- Social Robot Interaction and HRI
- Image and Signal Denoising Methods
- BIM and Construction Integration
- Gene Regulatory Network Analysis
Université d'Orléans
2014-2024
Laboratoire Pluridisciplinaire de Recherche en Ingénierie des Systèmes, Mécanique et Energétique
2017-2024
Institut National des Sciences Appliquées Centre Val de Loire
2015-2022
École Nationale Supérieure d'Ingénieurs de Caen
2010-2014
GREYC
2010-2014
Centre National de la Recherche Scientifique
2010-2014
Université de Caen Normandie
2011-2014
In this paper, we introduce a new class of non-local <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</i> -Laplacian operators that interpolate between Laplacian and infinity Laplacian. These are discrete analogous the game -laplacian on Euclidean spaces, involve morphological gradient graphs. We study Dirichlet problem associated with equation prove existence uniqueness it's solution. also consider diffusion graphs involving these operators....
Game-theoretic p -Laplacian or normalized operator is a version of classical variational which was introduced recently in connection with stochastic games called Tug-of-War noise (Peres et al . 2008, Tug-of-war noise: A game-theoretic view the -laplacian. Duke Mathematical Journal 145 (1), 91–120). In this paper, we propose an adaptation and generalization on weighted graphs for 1 ≤ ∞. This leads to partial difference combination between 1-Laplace, infinity-Laplace 2-Laplace operators...
The purpose of this paper is to develop a wrapper Random Forest-based feature selection method and study the performance on emotion recognition different selected sets. A large bank Gabor filters used extract face appearance. then applied wide set based importance score computed by Forest. multi-class SVM finally trained chosen features using widely database (CK+ database). Results show impact rate reveal that anger, sadness neutral expression increased selection.
In this paper we propose an adaptation of PDEs level sets over weighted graphs arbitrary structure, based on PdEs and using a framework discrete operators. A general formulation is presented algorithm to solve such equation described. Some transcriptions well-known models under formalism, as the mean-curvature-motion or active contours, are also provided. Then, present several applications our including image segmentation with topologies.
In this paper, we use the framework of partial difference equations on weighted graphs as a methodology to address problem computer-aided cytology. First, introduced perform image smoothing and filtering, has recently been extended segmentation semi-supervised clustering any discrete domain that can be represented by graph arbitrary topology. particular, unifies methods from processing machine learning communities within same formulation. We demonstrate method also used effectively unify...
In this paper, we propose an adaptation of partial difference equations (PDEs) level set method for nonmonotonic front propagation on weighted graphs. This leads to a PDE, whose coefficients are data geometry dependent. Our motivation is extend their applications any discrete that can be represented by graph. paper follows several preliminaries our works, and introduces significant improvements: A simplified explicit representation graph, new formulation the equation graphs considering both...
In this paper, we propose a new graph-based approach to address the problem of cytological computer-aided diagnostic. Such uses our previously introduced formalism PdEs-based morphology and geometric diffusion on graphs. The is illustrated through two applications in cytopathology (involving Feulgen Papanicolaou colorations), with examples nucleus extraction classification.
The preservation of historical monuments presents a formidable challenge, particularly in monitoring the deterioration building materials over time. Chateau de Chambord’s facade suffers from common issues such as flaking and spalling, which require meticulous stone joint mapping experts manually for restoration efforts. Advancements computer vision have allowed machine-learning models to help automatic segmentation process. In this research, custom architecture defined SAM-SVM is proposed,...