Since october 2017, I am a post-doc in the statistics department at Duke university. I work here with David Dunson and Jana Schaich Borg on statistics on human faces applied to social sciences. Before that I was a post-doc at the Weizmann Institute of Science where I worked with Ronen Basri. I obtained my phd in mathematical morphology (image processing) in november 2015 at Ecole des Mines de Paris under the supervision of Jesus Angulo.

My main fields of interest are:

  • applied Riemannian geometry
  • density estimation (in random and deterministic contexts)
  • non-scalar mathematical morphology
  • color science

Videos

GSI 2017: A family of anisotropic distributions on the hyperbolic space

GSI 2015: Probability density estimation on the hyperbolic space applied to radar processing

GSI 2015: Histograms of images valued in the manifold of colours endowed with perceptual metrics

Publications

Journals

Chevallier, E.; Chevallier, A.; Weiskopf, D. Histograms for functions on simplicial complexes. Submitted.

Chevallier, E.; Farup, I. Interpolation of the MacAdam ellipses. Accepted under revisions at SIAM Journal on Imaging Sciences.

Chevallier, E.; Kalunga, E.; Angulo, J. Kernel density estimation on spaces of Gaussian distributions and symmetric positive definite matrices. In SIAM Journal on Imaging Sciences; 2017,10 (1), 191–215

Chevallier, E.; Chevallier,A.; Angulo, J. N-ary Mathematical Morphology. In Mathematical Morphology - Theory and Applications; 2016,1(1), 339-350.

Chevallier, E.; Angulo, J. The Irregularity Issue of Total Orders on Metric Spaces and Its Consequences for Mathematical Morphology. In Journal of Mathematical Imaging and Vision; 2016,54(3), 344-357.

Chevallier, E.; Barbaresco, F.; Forget, T.; Angulo, J. Kernel Density Estimation on the Siegel Space with an Application to Radar Processing. In Entropy; 2016, 18(16), 396.

peer-reviewed conferences

Chevallier, E. A family of anisotropic distributions on the hyperbolic plane. In International Conference on Geometric Science of Information, Springer International Publishing; 2017, 717-724.

Forget, T.; Barbaresco, F.;Chevallier, E. ; Angulo, J. Doppler spectrum segmentation of radar sea clutter by mean-shift and information geometry metric. In 17th International Radar Symposium (IRS); IEEE; 2016, 1-6.

Chevallier, E.; Barbaresco, F.; Angulo, J. Probability density estimation on the hyperbolic space applied to radar processing. In International Conference on Geometric Science of Information; Springer International Publishing; 2015, 753-761.

Chevallier, E.; Farup, I.; Angulo, J. Histograms of images valued in the manifold of colours endowed with perceptual metrics. In International Conference on Geometric Science of Information}; Springer International Publishing; 2015, 762-769.

Chevallier, E.; Angulo, J. Image adapted total ordering for mathematical morphology on multivariate images. In International Conference on Image Processing (ICIP); IEEE; 2014, 2943-2947.

Chevallier, E.; Chevallier,A. ; Angulo, J. Computing Histogram of Tensor Images Using Orthogonal Series Density Estimation and Riemannian Metrics. In International Conference on Pattern Recognition (ICPR); IEEE; 2014.

Teaching

  • Spring 2018: teaching assistant for the undergraduate course STA 111 Probability and Statistics at Duke university
  • Fall 2016: teaching assistant for the MAREVA project (3rd year) at the Ecole des Mines de Paris
  • Fall 2013: lab assistant for the course of mathematical morphology at the Ecole des Mines de Paris