Eliminating artefacts in polarimetric images using deep learning

D. Paranjpye, A. Mahabal, A. N. Ramaprakash, G.V. Panopoulou, K. Cleary, A. C. S. Readhead, D. Blinov, K. Tassis

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

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 per cent true positive and 97 per cent true negative rates. Such models, combined with transfer learning, will give us a running start in artefact elimination for near-future surveys like WALOP.

Original languageEnglish
Pages (from-to)5151-5157
JournalMonthly Notices of the Royal Astronomical Society
Volume491
Issue number4
Early online date28 Nov 2019
DOIs
StatePublished - Feb 2020
Externally publishedYes

Keywords

  • deep learning
  • image classication
  • artefect detection
  • polarmetry

Fingerprint

Dive into the research topics of 'Eliminating artefacts in polarimetric images using deep learning'. Together they form a unique fingerprint.

Cite this