Deep learning early stopping for non-degenerate ghost imaging

Abstract Quantum ghost imaging offers many advantages over classical imaging, including the ability to probe an object with one wavelength and record the image with another (non-degenerate ghost imaging), but suffers from slow image reconstruction due to sparsity and probabilistic arrival positions...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Chané Moodley, Bereneice Sephton, Valeria Rodríguez-Fajardo, Andrew Forbes
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/86e61cc9ded94cc88b34a3e28f3530c2
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:86e61cc9ded94cc88b34a3e28f3530c2
record_format dspace
spelling oai:doaj.org-article:86e61cc9ded94cc88b34a3e28f3530c22021-12-02T18:27:49ZDeep learning early stopping for non-degenerate ghost imaging10.1038/s41598-021-88197-52045-2322https://doaj.org/article/86e61cc9ded94cc88b34a3e28f3530c22021-04-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-88197-5https://doaj.org/toc/2045-2322Abstract Quantum ghost imaging offers many advantages over classical imaging, including the ability to probe an object with one wavelength and record the image with another (non-degenerate ghost imaging), but suffers from slow image reconstruction due to sparsity and probabilistic arrival positions of photons. Here, we propose a two-step deep learning approach to establish an optimal early stopping point based on object recognition, even for sparsely filled images. In step one we enhance the reconstructed image after every measurement by a deep convolutional auto-encoder, followed by step two in which a classifier is used to recognise the image. We test this approach on a non-degenerate ghost imaging setup while varying physical parameters such as the mask type and resolution. We achieved a fivefold decrease in image acquisition time at a recognition confidence of $$75\%$$ 75 % . The significant reduction in experimental running time is an important step towards real-time ghost imaging, as well as object recognition with few photons, e.g., in the detection of light sensitive structures.Chané MoodleyBereneice SephtonValeria Rodríguez-FajardoAndrew ForbesNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-9 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Chané Moodley
Bereneice Sephton
Valeria Rodríguez-Fajardo
Andrew Forbes
Deep learning early stopping for non-degenerate ghost imaging
description Abstract Quantum ghost imaging offers many advantages over classical imaging, including the ability to probe an object with one wavelength and record the image with another (non-degenerate ghost imaging), but suffers from slow image reconstruction due to sparsity and probabilistic arrival positions of photons. Here, we propose a two-step deep learning approach to establish an optimal early stopping point based on object recognition, even for sparsely filled images. In step one we enhance the reconstructed image after every measurement by a deep convolutional auto-encoder, followed by step two in which a classifier is used to recognise the image. We test this approach on a non-degenerate ghost imaging setup while varying physical parameters such as the mask type and resolution. We achieved a fivefold decrease in image acquisition time at a recognition confidence of $$75\%$$ 75 % . The significant reduction in experimental running time is an important step towards real-time ghost imaging, as well as object recognition with few photons, e.g., in the detection of light sensitive structures.
format article
author Chané Moodley
Bereneice Sephton
Valeria Rodríguez-Fajardo
Andrew Forbes
author_facet Chané Moodley
Bereneice Sephton
Valeria Rodríguez-Fajardo
Andrew Forbes
author_sort Chané Moodley
title Deep learning early stopping for non-degenerate ghost imaging
title_short Deep learning early stopping for non-degenerate ghost imaging
title_full Deep learning early stopping for non-degenerate ghost imaging
title_fullStr Deep learning early stopping for non-degenerate ghost imaging
title_full_unstemmed Deep learning early stopping for non-degenerate ghost imaging
title_sort deep learning early stopping for non-degenerate ghost imaging
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/86e61cc9ded94cc88b34a3e28f3530c2
work_keys_str_mv AT chanemoodley deeplearningearlystoppingfornondegenerateghostimaging
AT bereneicesephton deeplearningearlystoppingfornondegenerateghostimaging
AT valeriarodriguezfajardo deeplearningearlystoppingfornondegenerateghostimaging
AT andrewforbes deeplearningearlystoppingfornondegenerateghostimaging
_version_ 1718377990451101696