Cargando…
Deep learning to enable color vision in the dark
Humans perceive light in the visible spectrum (400-700 nm). Some night vision systems use infrared light that is not perceptible to humans and the images rendered are transposed to a digital display presenting a monochromatic image in the visible spectrum. We sought to develop an imaging algorithm p...
Autores principales: | , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8985995/ https://www.ncbi.nlm.nih.gov/pubmed/35385502 http://dx.doi.org/10.1371/journal.pone.0265185 |
_version_ | 1784682460301230080 |
---|---|
author | Browne, Andrew W. Deyneka, Ekaterina Ceccarelli, Francesco To, Josiah K. Chen, Siwei Tang, Jianing Vu, Anderson N. Baldi, Pierre F. |
author_facet | Browne, Andrew W. Deyneka, Ekaterina Ceccarelli, Francesco To, Josiah K. Chen, Siwei Tang, Jianing Vu, Anderson N. Baldi, Pierre F. |
author_sort | Browne, Andrew W. |
collection | PubMed |
description | Humans perceive light in the visible spectrum (400-700 nm). Some night vision systems use infrared light that is not perceptible to humans and the images rendered are transposed to a digital display presenting a monochromatic image in the visible spectrum. We sought to develop an imaging algorithm powered by optimized deep learning architectures whereby infrared spectral illumination of a scene could be used to predict a visible spectrum rendering of the scene as if it were perceived by a human with visible spectrum light. This would make it possible to digitally render a visible spectrum scene to humans when they are otherwise in complete “darkness” and only illuminated with infrared light. To achieve this goal, we used a monochromatic camera sensitive to visible and near infrared light to acquire an image dataset of printed images of faces under multispectral illumination spanning standard visible red (604 nm), green (529 nm) and blue (447 nm) as well as infrared wavelengths (718, 777, and 807 nm). We then optimized a convolutional neural network with a U-Net-like architecture to predict visible spectrum images from only near-infrared images. This study serves as a first step towards predicting human visible spectrum scenes from imperceptible near-infrared illumination. Further work can profoundly contribute to a variety of applications including night vision and studies of biological samples sensitive to visible light. |
format | Online Article Text |
id | pubmed-8985995 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-89859952022-04-07 Deep learning to enable color vision in the dark Browne, Andrew W. Deyneka, Ekaterina Ceccarelli, Francesco To, Josiah K. Chen, Siwei Tang, Jianing Vu, Anderson N. Baldi, Pierre F. PLoS One Research Article Humans perceive light in the visible spectrum (400-700 nm). Some night vision systems use infrared light that is not perceptible to humans and the images rendered are transposed to a digital display presenting a monochromatic image in the visible spectrum. We sought to develop an imaging algorithm powered by optimized deep learning architectures whereby infrared spectral illumination of a scene could be used to predict a visible spectrum rendering of the scene as if it were perceived by a human with visible spectrum light. This would make it possible to digitally render a visible spectrum scene to humans when they are otherwise in complete “darkness” and only illuminated with infrared light. To achieve this goal, we used a monochromatic camera sensitive to visible and near infrared light to acquire an image dataset of printed images of faces under multispectral illumination spanning standard visible red (604 nm), green (529 nm) and blue (447 nm) as well as infrared wavelengths (718, 777, and 807 nm). We then optimized a convolutional neural network with a U-Net-like architecture to predict visible spectrum images from only near-infrared images. This study serves as a first step towards predicting human visible spectrum scenes from imperceptible near-infrared illumination. Further work can profoundly contribute to a variety of applications including night vision and studies of biological samples sensitive to visible light. Public Library of Science 2022-04-06 /pmc/articles/PMC8985995/ /pubmed/35385502 http://dx.doi.org/10.1371/journal.pone.0265185 Text en © 2022 Browne et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. |
spellingShingle | Research Article Browne, Andrew W. Deyneka, Ekaterina Ceccarelli, Francesco To, Josiah K. Chen, Siwei Tang, Jianing Vu, Anderson N. Baldi, Pierre F. Deep learning to enable color vision in the dark |
title | Deep learning to enable color vision in the dark |
title_full | Deep learning to enable color vision in the dark |
title_fullStr | Deep learning to enable color vision in the dark |
title_full_unstemmed | Deep learning to enable color vision in the dark |
title_short | Deep learning to enable color vision in the dark |
title_sort | deep learning to enable color vision in the dark |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8985995/ https://www.ncbi.nlm.nih.gov/pubmed/35385502 http://dx.doi.org/10.1371/journal.pone.0265185 |
work_keys_str_mv | AT browneandreww deeplearningtoenablecolorvisioninthedark AT deynekaekaterina deeplearningtoenablecolorvisioninthedark AT ceccarellifrancesco deeplearningtoenablecolorvisioninthedark AT tojosiahk deeplearningtoenablecolorvisioninthedark AT chensiwei deeplearningtoenablecolorvisioninthedark AT tangjianing deeplearningtoenablecolorvisioninthedark AT vuandersonn deeplearningtoenablecolorvisioninthedark AT baldipierref deeplearningtoenablecolorvisioninthedark |