English

Eliminating artefacts in Polarimetric Images using Deep Learning

Machine Learning 2019-12-02 v1 Instrumentation and Methods for Astrophysics Machine Learning

Abstract

Polarization measurements done using Imaging Polarimeters such as the Robotic Polarimeter are very sensitive to the presence of artefacts in images. Artefacts can range from internal reflections in a telescope to satellite trails that could contaminate an area of interest in the image. With the advent of wide-field polarimetry surveys, it is imperative to develop methods that automatically flag artefacts in images. In this paper, we implement a Convolutional Neural Network to identify the most dominant artefacts in the images. We find that our model can successfully classify sources with 98\% true positive and 97\% true negative rates. Such models, combined with transfer learning, will give us a running start in artefact elimination for near-future surveys like WALOP.

Keywords

Cite

@article{arxiv.1911.08327,
  title  = {Eliminating artefacts in Polarimetric Images using Deep Learning},
  author = {Dhruv Paranjpye and Ashish Mahabal and A. N. Ramaprakash and Gina Panopoulou and Kieran Cleary and Anthony Readhead and Dmitry Blinov and Kostas Tassis},
  journal= {arXiv preprint arXiv:1911.08327},
  year   = {2019}
}

Comments

7 pages, 15 figures

R2 v1 2026-06-23T12:20:45.978Z