D
David Brie
Researcher at University of Lorraine
Publications - 58
Citations - 1909
David Brie is an academic researcher from University of Lorraine. The author has contributed to research in topics: Sparse approximation & Hyperspectral imaging. The author has an hindex of 20, co-authored 52 publications receiving 1749 citations. Previous affiliations of David Brie include Centre national de la recherche scientifique & Nancy-Université.
Papers
More filters
Journal ArticleDOI
Background removal from spectra by designing and minimising a non-quadratic cost function
TL;DR: In this paper, the problem of estimating the background of a spectrum is addressed by fitting this background to a low-order polynomial, but rather than determining the polynomials that minimise a least-squares criterion (i.e., a quadratic cost function), non-quadratic cost functions well adapted to the problem are proposed.
Journal ArticleDOI
Separation of Non-Negative Mixture of Non-Negative Sources Using a Bayesian Approach and MCMC Sampling
TL;DR: A Markov chain Monte Carlo (MCMC) sampling procedure is proposed to simulate the resulting joint posterior density from which marginal posterior mean estimates of the source signals and mixing coefficients are obtained.
Journal ArticleDOI
From Bernoulli–Gaussian Deconvolution to Sparse Signal Restoration
TL;DR: This work revisits the single most likely replacement (SMLR) algorithm and shows that the formulation of sparse signal restoration as a limit case of Bernoulli-Gaussian signal restoration leads to an l0-penalized least square minimization problem, to which SMLR can be straightforwardly adapted.
Journal ArticleDOI
On the decomposition of Mars hyperspectral data by ICA and Bayesian positive source separation
Saïd Moussaoui,Hafrun Hauksdottir,Frédéric Schmidt,Christian Jutten,Jocelyn Chanussot,David Brie,Sylvain Douté,Jon Atli Benediktsson +7 more
TL;DR: A combination of spatial ICA with spectral Bayesian positive source (BPSS) with a rough classification of pixels is proposed, which allows selection of small, but relevant, number of pixels for the component extraction and consequently the endmember classification.
Journal ArticleDOI
Automated force volume image processing for biological samples.
TL;DR: Two algorithms are proposed, one for the processing of approach force curves and another for the quantitative analysis of retraction force curves, to provide fully automated tools to achieve theoretical interpretation of force curves on the basis of adequate, available physical models.