D
David Rousseau
Researcher at University of Angers
Publications - 183
Citations - 2935
David Rousseau is an academic researcher from University of Angers. The author has contributed to research in topics: Stochastic resonance & Noise (signal processing). The author has an hindex of 24, co-authored 176 publications receiving 2374 citations. Previous affiliations of David Rousseau include University of Lyon & Institut national de la recherche agronomique.
Papers
More filters
Journal ArticleDOI
Application note: Thermography versus chlorophyll fluorescence imaging for detection and quantification of apple scab
TL;DR: A comparison of these two techniques is undertaken and the advantages of thermal imaging compared to fluorescence imaging are demonstrated to detect and quantify the presence of apple scab at the surface of leaves.
Journal ArticleDOI
Novel data augmentation strategies to boost supervised segmentation of plant disease
Clément Douarre,Clément Douarre,Carlos Crispim-Junior,Anthony Gelibert,Laure Tougne,David Rousseau +5 more
TL;DR: This article tackled for illustration with agricultural material the difficult segmentation task of apple scab on images of apple plant canopy by using convolutional neural networks and devised two novel methods of generating data based on a plant canopy simulation and the other on Generative Adversatial Networks (GANs).
Journal ArticleDOI
Multiscale imaging of plants: current approaches and challenges.
David Rousseau,Yann Chéné,Etienne Belin,Georges Semaan,Ghassen Trigui,Karima Boudehri,Florence Franconi,François Chapeau-Blondeau +7 more
TL;DR: It is discussed how this renews the interest for multiscale image processing tools such as wavelets, fractals and recent variants to analyse such high-resolution images.
Nonlinear estimation from quantized signals: quantizer optimization and stochastic resonance.
David Rousseau,G. V. Anand +1 more
TL;DR: This work considers a parameter estimation task performed on a signal buried in noise by means of a quantized representation by a two-level quantizer of the signal-plus-noise mixture, and shows that the performance for estimation can be maximized by an optimal choice of the quantization threshold.
Journal ArticleDOI
Open-CSAM, a new tool for semi-automated analysis of myofiber cross-sectional area in regenerating adult skeletal muscle
Thibaut Desgeorges,Sophie Liot,Solene Lyon,Jessica Bouvière,Alix Kemmel,Aurélie Trignol,David Rousseau,Bruno Chapuis,Julien Gondin,Rémi Mounier,Bénédicte Chazaud,Gaëtan Juban +11 more
TL;DR: Open-CSAM, an ImageJ macro, is developed to perform a high throughput semi-automated analysis of CSA on skeletal muscle from various experimental conditions and is shown to be more accurate to measure CSA in regenerating and dystrophic muscles as compared with SMASH, MyoVision, and MuscleJ softwares.