Standard

Eliminating artefacts in polarimetric images using deep learning. / Paranjpye, D.; Mahabal, A.; Ramaprakash, A. N.; Panopoulou, G.V.; Cleary, K.; Readhead, A. C. S.; Blinov, D.; Tassis, K.

In: Monthly Notices of the Royal Astronomical Society, Vol. 491, No. 4, 01.02.2020, p. 5151-5157.

Research output: Contribution to journal › Article › peer-review

Harvard

Paranjpye, D, Mahabal, A, Ramaprakash, AN, Panopoulou, GV, Cleary, K, Readhead, ACS, Blinov, D & Tassis, K 2020, 'Eliminating artefacts in polarimetric images using deep learning', Monthly Notices of the Royal Astronomical Society, vol. 491, no. 4, pp. 5151-5157. https://doi.org/10.1093/mnras/stz3250

APA

Paranjpye, D., Mahabal, A., Ramaprakash, A. N., Panopoulou, G. V., Cleary, K., Readhead, A. C. S., Blinov, D., & Tassis, K. (2020). Eliminating artefacts in polarimetric images using deep learning. Monthly Notices of the Royal Astronomical Society, 491(4), 5151-5157. https://doi.org/10.1093/mnras/stz3250

Vancouver

Paranjpye D, Mahabal A, Ramaprakash AN, Panopoulou GV, Cleary K, Readhead ACS et al. Eliminating artefacts in polarimetric images using deep learning. Monthly Notices of the Royal Astronomical Society. 2020 Feb 1;491(4):5151-5157. https://doi.org/10.1093/mnras/stz3250

Author

Paranjpye, D. ; Mahabal, A. ; Ramaprakash, A. N. ; Panopoulou, G.V. ; Cleary, K. ; Readhead, A. C. S. ; Blinov, D. ; Tassis, K. / Eliminating artefacts in polarimetric images using deep learning. In: Monthly Notices of the Royal Astronomical Society. 2020 ; Vol. 491, No. 4. pp. 5151-5157.

BibTeX

@article{b43842782d6f4c43a4e033a1df334531,
title = "Eliminating artefacts in polarimetric images using deep 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 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.",
keywords = "deep learning, image classication, artefect detection, polarmetry, Deep learning, Artefect detection, Image classication, Polarmetry, Artefact detection, Polarimetry, Image classification",
author = "D. Paranjpye and A. Mahabal and Ramaprakash, {A. N.} and G.V. Panopoulou and K. Cleary and Readhead, {A. C. S.} and D. Blinov and K. Tassis",
note = "Funding Information: The work has been funded by the National Science Foundation under the NSF grant (161547). AM acknowledges support from the NSF (1640818, AST-1815034) and IUSSTF (JC-001/2017). KT acknowledges support from the European Research Council under the European Union?s Horizon 2020 research and innovation program, under grant agreement no. 771282. Publisher Copyright: {\textcopyright} 2019 The Author(s).",
year = "2020",
month = feb,
day = "1",
doi = "10.1093/mnras/stz3250",
language = "Английский",
volume = "491",
pages = "5151--5157",
journal = "Monthly Notices of the Royal Astronomical Society",
issn = "0035-8711",
publisher = "Wiley-Blackwell",
number = "4",

}

RIS

TY - JOUR

T1 - Eliminating artefacts in polarimetric images using deep learning

AU - Paranjpye, D.

AU - Mahabal, A.

AU - Ramaprakash, A. N.

AU - Panopoulou, G.V.

AU - Cleary, K.

AU - Readhead, A. C. S.

AU - Blinov, D.

AU - Tassis, K.

N1 - Funding Information: The work has been funded by the National Science Foundation under the NSF grant (161547). AM acknowledges support from the NSF (1640818, AST-1815034) and IUSSTF (JC-001/2017). KT acknowledges support from the European Research Council under the European Union?s Horizon 2020 research and innovation program, under grant agreement no. 771282. Publisher Copyright: © 2019 The Author(s).

PY - 2020/2/1

Y1 - 2020/2/1

N2 - 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.

AB - 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.

KW - deep learning

KW - image classication

KW - artefect detection

KW - polarmetry

KW - Deep learning

KW - Artefect detection

KW - Image classication

KW - Polarmetry

KW - Artefact detection

KW - Polarimetry

KW - Image classification

UR - http://www.scopus.com/inward/record.url?scp=85096958447&partnerID=8YFLogxK

UR - https://www.mendeley.com/catalogue/5d353726-a24a-3dee-b358-3817849d2643/

U2 - 10.1093/mnras/stz3250

DO - 10.1093/mnras/stz3250

M3 - статья

VL - 491

SP - 5151

EP - 5157

JO - Monthly Notices of the Royal Astronomical Society

JF - Monthly Notices of the Royal Astronomical Society

SN - 0035-8711

IS - 4

ER -

ID: 51921049