|
|
Sylvain Prigent
Doctorant
 Mots-clés : Segmentation, Classification
 Démo : voir la démo de l'auteur
 Contact :
| E-Mail : | | SylvaindotPrigentatinriadotfr | | Téléphone : | | (33)4-97-15-53-68 | | Fax : | | (33)4-92-38-76-43 | | Adresse : | | INRIA Sophia Antipolis
2004, route des Lucioles
06902 Sophia Antipolis Cedex
France |
|
| Résumé :
Les images hyper-spectrales consistent en une même scène acquise à différentes longueurs d’onde. De telles images permettent d'analyser un objet ou une scène de par, à la fois, ses propriétés spatiales et spectrales. L'objectif de ma thèse, en collaboration avec Galderma (entreprise pharmaceutique spécialisée en dermatologie, ayant pour actionnaires L'Oréal et Nestlé) est de caractériser les lésions cutanées à partir d'images multi et hyper-spectrales. Pour cela, nous nous intéressons aux outils d'analyse spectrale et de réduction de données tels que l'analyse en composantes principales (ACP), l'analyse en composantes indépendantes (ACI) ou encore la poursuite de projection, ainsi qu'aux outils de classification comme les séparateurs à vaste marge (SVM) par exemple.
Ce travail de thèse fait suite à mon stage de Master recherche dans le projet Ariana (de février à septembre 2009) qui a donner lieu au dépôt de 2 brevets, OA09437 et OA09438, déposés fin Novembre 2009 (50% INRIA, 50% Galderma). |
Mini CV :
 2009-2012: PhD in Ariana project (INRIA Sophia Antipolis, France), in collaboration with Galderma R&D (Sophia Antipolis, France)
2008-2009 : Master SIPT (Signal Image Parole Telecom,), with Honours (A) - Grenoble
2006-2009 : Engineering school, Institut National Polytechnique de Grenoble , ENSIEG-ENSE3 Image and signal processing. |
Dernières publications dans le projet Ariana :
Estimation of an optimal spectral band combination to evaluate skin disease treatment efficacy using multi-spectral images.
S. Prigent et D. Zugaj et X. Descombes et P. Martel et J. Zerubia. Dans Proc. IEEE International Conference on Image Processing (ICIP), Brussels, Belgium, septembre 2011.
@INPROCEEDINGS{prigent11a,
|
| author |
= |
{Prigent, S. and Zugaj, D. and Descombes, X. and Martel, P. and Zerubia, J.}, |
| title |
= |
{Estimation of an optimal spectral band combination to evaluate skin disease treatment efficacy using multi-spectral images}, |
| year |
= |
{2011}, |
| month |
= |
{septembre}, |
| booktitle |
= |
{Proc. IEEE International Conference on Image Processing (ICIP)}, |
| address |
= |
{Brussels, Belgium}, |
| pdf |
= |
{http://hal.inria.fr/docs/00/59/06/94/PDF/icip_final.pdf}, |
| keyword |
= |
{} |
| } |
Abstract :
Clinical evaluation of skin treatments consists of two steps. First, the degree of the disease is measured clinically on a group of patients by dermatologists. Then, a statistical test is used on obtained set of measures to determine the treatment efficacy. In this paper, a method is proposed to automatically measure the severity of skin hyperpigmentation. After a classification step, an objective function is designed in order to obtain an optimal linear combination of bands defining the severity criterion. Then a hypothesis test is deployed on this combination to quantify treatment efficacy. |
Multi-spectral Image Analysis for Skin Pigmentation Classification.
S. Prigent et X. Descombes et D. Zugaj et P. Martel et J. Zerubia. Dans Proc. IEEE International Conference on Image Processing (ICIP), Hong-Kong, China, septembre 2010.
Mots-clés : skin hyper-pigmentation, Multi-spectral images, Support Vector Machines, Independant Component Analysis, Data reduction.
@INPROCEEDINGS{sp02,
|
| author |
= |
{Prigent, S. and Descombes, X. and Zugaj, D. and Martel, P. and Zerubia, J.}, |
| title |
= |
{Multi-spectral Image Analysis for Skin Pigmentation Classification}, |
| year |
= |
{2010}, |
| month |
= |
{septembre}, |
| booktitle |
= |
{Proc. IEEE International Conference on Image Processing (ICIP)}, |
| address |
= |
{Hong-Kong, China}, |
| pdf |
= |
{http://hal.inria.fr/docs/00/49/94/92/PDF/Article_ICIP.pdf}, |
| keyword |
= |
{skin hyper-pigmentation, Multi-spectral images, Support Vector Machines, Independant Component Analysis, Data reduction} |
| } |
Abstract :
In this paper, we compare two different approaches for semi-automatic detection of skin hyper-pigmentation on multi-spectral images. These two methods are support vector machine (SVM) and blind source separation. To apply SVM, a dimension reduction method adapted to data classification is proposed. It allows to improve the quality of SVM classification as well as to have reasonable computation time. For the blind source separation approach we show that, using independent component analysis, it is possible to extract a relevant cartography of skin pigmentation.
|
Spectral Analysis and Unsupervised SVM Classification for Skin Hyper-pigmentation Classification.
S. Prigent et X. Descombes et D. Zugaj et J. Zerubia. Dans Proc. IEEE Workshop on Hyperspectral Image and Signal Processing : Evolution in Remote Sensing (WHISPERS), Reykjavik, Iceland, juin 2010.
Mots-clés : Sectral analysis, Data reduction, Projection pursuit, Support Vector Machines, skin hyper-pigmentation.
@INPROCEEDINGS{sp01,
|
| author |
= |
{Prigent, S. and Descombes, X. and Zugaj, D. and Zerubia, J.}, |
| title |
= |
{Spectral Analysis and Unsupervised SVM Classification for Skin Hyper-pigmentation Classification}, |
| year |
= |
{2010}, |
| month |
= |
{juin}, |
| booktitle |
= |
{Proc. IEEE Workshop on Hyperspectral Image and Signal Processing : Evolution in Remote Sensing (WHISPERS)}, |
| address |
= |
{Reykjavik, Iceland}, |
| pdf |
= |
{http://hal.inria.fr/docs/00/49/55/60/PDF/whispers2010_submission_124.pdf}, |
| keyword |
= |
{Sectral analysis, Data reduction, Projection pursuit, Support Vector Machines, skin hyper-pigmentation} |
| } |
Abstract :
Data reduction procedures and classification via support vector machines (SVMs) are often associated with multi or hyperspectral image analysis. In this paper, we propose an automatic method with these two schemes in order to perform a classification of skin hyper-pigmentation on multi-spectral images. We propose a spectral analysis method to partition the spectrum as a tool for data reduction, implemented by projection pursuit. Once the data is reduced, an SVM is used to differentiate the pathological from the healthy areas. As SVM is a supervised classification method, we propose a spatial criterion for spectral analysis in order to perform automatic learning. |
|
Liste complète des publications dans le projet Ariana
|
|
Nouvelle page de démos
