Former projects


Microarray images push to their limits classical analysis methods. New approaches are thus needed to ensure accurate data extraction from these images

Image processing on volcanoes

Analysis of thermal videos of volcanoes

Machine Learning in Brain Data Processing

Machine Learning in Brain Data Processing

Satellite Image Processing.

Use of Hidden Markov Models and non stationarity to process temporal satellite Images.

Topographic Analysis of Electrode Contacts in Human Cortical Stimulation

Automatic tool for topographic analysis able to compute 2D maps from the 3D anatomic MRI.

Transcranial Magnetic Stimulation

Development of a TMS simulator.

3D shape retrieval

3D shape retrieval using kernels on graphs.

Analysis of Segmentation Methods

First step our our longstanding collaboration with the University of Bergen, in Norway.

Anatomical / Functional Image Fusion

General framework for the fusion of Anatomical and Functional Images.

Brain image segmentation

Unsupervised fuzzy classification scheme for brain tissue segmentation

Cutting Organic Surfaces

Decomposition of surfaces into quadrangle regions.

Fusion of Image/Expert information

Aggregation between a MR image and information resulting from expert knowledge.

Low-resolution Surface Mapping

Mapping a surface onto a piece of the plane, using low resolution acquisitions.

MR/MR Image Fusion

Quantification of brain tissues using multispectral MR images fusion.

Modular Ensemble Tracking

Tracking of objects in videos using MCMC and Ensemble methods

Solar Image Processing

Variability Analysis of the solar corona and the monitoring of its traditional regions

Surface quadrangulations using scalar functions

Decomposition of surfaces into quadrangle regions.

Surface tiling

Tiling image with cylinders using n-loops.

Thigh Image Processing

Segmentation of muscle and fat compartments from MR images of thighs

Topology correction of brain surfaces

Combined, voxel and surface based, topology correction method.

Recent Publications

More Publications

. A non-stationary NDVI time series modelling using triplet Markov chain. In International Journal of Information and Decision Sciences, 2018.


. Apprentissage artificiel - 3e édition: Concepts et algorithmes. Eds. Eyrolles, 2018.

Buy online

. A new feature selection approach based on ensemble methods in semi-supervised classification. Pattern Analysis and Applications, 20,3:673-686, 2017.

PDF bibtex

. Semi-supervised superpixel classification for medical images segmentation : application to detection of glaucoma disease. Multidimensional Systems and Signal Processing, 2017.

PDF bibtex

Selected Publications

Nowadays, vegetation monitoring using remotely sensed data is an important far-reaching real-world issue. The main purpose of this study is to build a triplet Markov chain (TMC) to model and analyse vegetation dynamics on large-scales using non-stationary normalised difference vegetation index (NDVI) time series. TMC is a generalisation of hidden Markov models (HMMs), which have been widely used to represent satellite time series images but which they proved to be inefficient for non-stationary data. The TMC model proposed in this paper overcomes this limit by adding an auxiliary process which allows modelling non-stationarity. In order to assess the performance of the proposed model, experimentation is carried out using moderate resolution imaging spectroradiometer (MODIS) NDVI time series of the north-western region of Tunisia. The TMC model is compared to standard HMM and seasonal auto regressive integrated moving average model (SARIMA) and proved to achieve the best performance with an overall accuracy prediction rate of 92.8% and a kappa coefficient of 0.885.
In International Journal of Information and Decision Sciences, 2018.

Over the last decade, feature tracking and recognition in infrared (IR) video has become an important strategy used in many applications. To achieve such a capability, we developed a method based on the top-hat transform, hybridized with refinement by thresholding. Our algorithm uses two different but correlated background subtraction approaches to clean the image. A mathematical-morphology-based method was then applied to enhance the contrast between particles and background. The algorithm was tested using images acquired during a controlled experiment and was compared with another particle tracking velocimetry method. We demonstrate that our algorithm can detect dim IR targets and enables computation of a local velocity field that can be used for the tracking step. Using this method, we were able to obtain both the distribution of particle sizes, volumes (or masses), and velocities. We also apply our algorithm to images recorded during ballistic emitting explosive events at Stromboli volcano (Italy) and favorably compare our results with other volcanologic data sets. Experimental results demonstrate that our algorithm achieves a high recognition accuracy with a low-computational cost.
In Journal of Applied Remote Sensing, 8(1), 083549, 2014.

3D shape retrieval is becoming an acute issue for numerous applications that span from CAD to serious games to biomedicine and all contexts where it is fundamental to automatically retrieve geometric information from a collection of 3D models. This paper addresses 3D shape retrieval in terms of a graph-based description and the definition of a corresponding similarity measure. For this purpose, 3D models are represented as bags of shortest paths defined over well chosen Extended Reeb Graphs, while the similarity between pairs of Extended Reeb Graphs is addressed through kernels adapted to these descriptions. Results are comparable with the best results of the literature, and the modularity and evolutivity of the method ensure its applicability to other problems, from partial shape matching to classification.
In Pattern Recognition, 46:2985–2999, 2013.

Magnetic resonance (MR) provides a non-invasive way to investigate changes in the brain resulting from aging or neurodegenerative disorders such as Alzheimer’s disease (AD). Performing accurate analysis for population studies is challenging because of the interindividual anatomical variability. A large set of tools is found to perform studies of brain anatomy and population analysis (FreeSurfer, SPM, FSL). In this paper we present a newly developed surface-based processing pipeline (MILXCTE) that allows accurate vertex-wise statistical comparisons of brain modifications, such as cortical thickness (CTE). The brain is first segmented into the three main tissues: white matter, gray matter and cerebrospinal fluid, after CTE is computed, a topology corrected mesh is generated. Partial inflation and non-rigid registration of cortical surfaces to a common space using shape context are then performed. Each of the steps was firstly validated using MR images from the OASIS database. We then applied the pipeline to a sample of individuals randomly selected from the AIBL study on AD and compared with FreeSurfer. For a population of 50 individuals we found correlation of cortical thickness in all the regions of the brain (average r = 0.62 left and r = 0.64 right hemispheres). We finally computed changes in atrophy in 32 AD patients and 81 healthy elderly individuals. Significant differences were found in regions known to be affected in AD. We demonstrated the validity of the method for use in clinical studies which provides an alternative to well established techniques to compare different imaging biomarkers for the study of neurodegenerative diseases.
In Journal of Neuroscience Methods, 205:96-109, 2012.

The study of the variability of the solar corona and the monitoring of coronal holes, quiet sun and active regions are of great importance in astrophysics as well as for space weather and space climate applications. In a previous work, we presented the spatial possibilistic clustering algorithm (SPoCA). This is a multi-channel unsupervised spatially-constrained fuzzy clustering method that automatically segments solar extreme ultraviolet (EUV) images into regions of interest. The results we reported on SoHO-EIT images taken from February 1997 to May 2005 were consistent with previous knowledge in terms of both areas and intensity estimations. However, they presented some artifacts due to the method itself. Herein, we propose a new algorithm, based on SPoCA, that removes these artifacts. We focus on two points: the definition of an optimal clustering with respect to the regions of interest, and the accurate definition of the cluster edges. We moreover propose methodological extensions to this method, and we illustrate these extensions with the automatic tracking of active regions. The much improved algorithm can decompose the whole set of EIT solar images over the 23rd solar cycle into regions that can clearly be identified as quiet sun, coronal hole and active region. The variations of the parameters resulting from the segmentation, i.e. the area, mean intensity, and relative contribution to the solar irradiance, are consistent with previous results and thus validate the decomposition. Furthermore, we find indications for a small variation of the mean intensity of each region in correlation with the solar cycle. The method is generic enough to allow the introduction of other channels or data. New applications are now expected, e.g. related to SDO-AIA data
In Astronomy and Astrophysics, 505, 361-371, 2009.

PhD Students

Current PhD students

  • FILLIERES G, Generation of tactile maps for visual impairs, september 2017 - september 2020 (50% G TOUYA, IGN and JM FAVREAU, LIMOS)
  • LE CORNEC K, Multimodal deep learning, september 2017 - september 2020
  • ATOCHE BRAVO J, Cloud blurring through satellite image processing, september 2016 - september 2019 (50% E Ocana, IMCA)

Past PhD students

  • BEN ABBESS A : Spatiotemporal satellite image analysis - september 2013 - december 2016. (50% R FARAH, ENSI Tunis)
  • SETTOUTI N, Semi supervised classification of medical data, septembre 2013- may 2016. (50% M CHIKH, Univ. Tlemcen)
  • GARCIA G, A software approach for the study of dyslexia, september 2011 – december 2015
  • BOMBRUN M, High temporal thermal imaging of volcanic plumes, september 2012 - october 2015. (50% A HARRIS, LMV)
  • BEN TOUHAMI H, Bayesian calibration and data mining for the study of climate changes, september 2011 – march 2014. (50% G BELLOCCHI, INRA)
  • HAEN C, SysEx: an expert system for System Administration, september 2010 - october 2013
  • ESSID H, Hybrid spatiotemporal models for the study of satellite images, september 2009 - december 2012. (50% R FARAH, ENSI Tunis)
  • PENNE T, Video tracking, september 2008 - october 2011 (50% C TILMANT, Univ Blaise Pascal)
  • LUQUET S, Transcranial magnetic stimulation, september 2005 - december 2009
  • FAVREAU JM, Some tools for surface unfolding, september 2006 - october 2009
  • MONTAGNER J, Multimodal fusion for the targeting and the quantification of cerebral structures and actitities, september 2001 - december 2004
  • FRENOUX E, Data fusion in brain image processing. Applications and validations, september 2000 - 17 december 2003


I am (or have been) a teaching instructor for the following courses :

ISIMA - Engineering school in Computer Science.

Current lectures

  • Deep Learning

    • Introduction to deep Learning and TensorFlow
    • Neural networks and MLP
    • CNN
    • Autoencoders
    • RNN
    • Transfer Learning
    • Introduction to Keras
    • Generative Adversarial Networks.
  • Machine Learning

    • Introduction to Machine Learning and scikit-learn
    • Linear models
    • Classification and clustering
    • Ensemble methods
    • Kernel methods
    • Model selection and manifold learning
    • Hidden Markov Models
  • Data Analysis

    • First and second order statistics
    • Linear dimension reductiob algorithms
    • Clustering and classification
  • Numerical analysis and linear algebra

    • Introduction to linear systems
    • numerical stability
    • Least squares and orthogonal transformations
    • Eigendecompositons
    • Positive definite matrices
    • Introduction to optimisation in finite dimension
  • Image Processing

    • Introduction to CImg
    • Spatial filtering
    • Filtering in the frequency domain
    • Diffusion filtering
    • Optical flow
    • Hough transform
    • Clustering and classification in image processing
    • Active contours
    • Image Segmentation

Past lectures

  • Introduction to stochastic differential equations
  • Linear Programming
  • Dynamic programming

Master’s degree

  • Elements of machine Learning
  • Hidden Markov Models
  • Probabilistic Image modeling: MRF and their applications

DUT (1998-2002)

  • Physics of acquisition systems
  • Graphic libraries: DirectX and OpenGL
  • Mathematics and CAD

Invited Professor

  • Univ of Jendouba (Tunisia): Markov Models in image processing



  • 2012-2017: Dean of ISIMA
  • 2006-2012: Head of the Mathematical and computer science department, ISIMA
  • 2007-2012: Head of the Master in Computer Science, Image Processing and Robotics, Blaise Pascal University
  • 2007-2016: Co-head of the Doctoral school “Engineering Sciences”, Clermont-Fd
  • 2012-present: Head of the G4 group at LIMOS

International collaborations

Image Processing

  • University of Bergen (Norway, Pr. A LUNDERVOLD)
  • NeuroImaging Lab, Los Angeles (LONI, UCLA) (USA, Dr V VIDAL)
  • Commonwealth Scientific and Industrial Research Organisation (CSIRO), Brisbane (Australia, Dr. O SALVADO)
  • Royal Observatory of Belgium, Brussels (Belgium, Dr V DELOUILLE)
  • Astronomic Institute, Sciences academy Ondrejov (Czech Republic , Pr. M SOBOTKA)
  • NASA, program number NNH08ZDA001N-SDOSC
  • RIADI-GDL Lab, Tunis (Tunisia, Dr. R FARAH)
  • Universidad Nacional de Ingenieria (IMCA), Instituto de Matematica y Ciencias Afines, Lima, (Peru, Pr E Ocana)

Computer Graphics

  • Institute of Applied Mathematics and Information Technology (IMATI), Genoa (Italia, Pr. M SPAGNUOLO)

Machine Learning

  • CERN (Switzerland, Dr. N NEUFELD)
  • John Hutton Institute, Aberdeen (Scotland, Dr. A GIMONA)

Organization of Scientific Manifestations

  • General co-chair of RFIA’2016, June 28-July 3 2016, Clermont-Fd, France
  • General co-chair of CAp’2010, May 17-19 2010, Clermont-Ferrand, France
  • Co organizisation of IBMISPS’2006 International Brain Mapping and Intraoperative Surgical Planning, September 4-8 2006, Clermont Fd, France
  • General co-chair of OICMS’05, the first Open International Conference on Modeling and Simulation, October 12-15 2005, Clermont-Fd, France
  • Organisation of the Scientific meetings of the Doctoral school in 2007, 2008 and 2010
  • Organisation of the national workshop of telemedecine, December 1999
  • Chairman of several conferences (VISAPP, COSI,..)

Reviewing activities

National and International Networks

  • Member of GDR ISIS and IM

Expertise of national and international programs

  • Reviewer of several french ACI’s
  • Reviewer of several french ANR projects (CSOSG, RIAM, TECSAN)
  • Expert for EAMBES, European Alliance for Medical and Biological Engineering and Science
  • Expert for FNRS, Fond de la Recherche Scientifique