Identifying contaminants in astronomical images using convolutional neural networks - CNRS - Centre national de la recherche scientifique Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

Identifying contaminants in astronomical images using convolutional neural networks

M. Paillassa
  • Fonction : Auteur
H. Bouy

Résumé

In this work, we propose to use convolutional neural networks to detect contaminants in astronomical images. Each contaminant is treated in a one vs all fashion. Once trained, our network is able to detect various contaminants such as cosmic rays, hot and bad pixel defaults, persistence effects, satellite trails or fringe patterns in images of various field properties. The convolutional neural network is performing semantic segmentation: it can output a probability map, assigning to each pixel its probability to belong to the contaminant or the background class. Training and testing data have been gathered from real or simulated data.
Fichier non déposé

Dates et versions

hal-01982125 , version 1 (15-01-2019)

Identifiants

Citer

M. Paillassa, E. Bertin, H. Bouy. Identifying contaminants in astronomical images using convolutional neural networks. Proceedings of the Annual meeting of the Frenh Society of Astronomy and Astrophysics. - 3 au 6 juillet 2018 – Bordeaux-France- SF2A-2018- Eds.: P. Di Matteo, F. Billebaud, F. Herpin, N. Lagarde, J.-B. Marquette, A. Robin, O. Venot,, Jul 2018, bordeaux, France. ⟨hal-01982125⟩

Collections

INSU CNRS L3AB
40 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More