Cargando…
Weibull Tone Mapping (WTM) for the Enhancement of Underwater Imagery
Domain experts prefer interactive and targeted control-point tone mapping operations (TMOs) to enhance underwater image quality and feature visibility; though this comes at the expense of time and training. In this paper, we provide end-users with a simpler and faster interactive tone-mapping approa...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10098941/ https://www.ncbi.nlm.nih.gov/pubmed/37050592 http://dx.doi.org/10.3390/s23073533 |
_version_ | 1785024935022821376 |
---|---|
author | Game, Chloe Amanda Thompson, Michael Barry Finlayson, Graham David |
author_facet | Game, Chloe Amanda Thompson, Michael Barry Finlayson, Graham David |
author_sort | Game, Chloe Amanda |
collection | PubMed |
description | Domain experts prefer interactive and targeted control-point tone mapping operations (TMOs) to enhance underwater image quality and feature visibility; though this comes at the expense of time and training. In this paper, we provide end-users with a simpler and faster interactive tone-mapping approach. This is built upon Weibull Tone Mapping (WTM) theory; introduced in previous work as a preferred tool to describe and improve domain expert TMOs. We allow end-users to easily shape brightness distributions according to the Weibull distribution, using two parameter sliders which modify the distribution peak and spread. Our experiments showed that 10 domain experts found the two-slider Weibull manipulation sufficed to make a desired adjustment in >80% of images in a large dataset. For the remaining ∼20%, observers opted for a control-point TMO which can, broadly, encompass many global tone mapping algorithms. Importantly, 91% of these control-point TMOs can actually be visually well-approximated by our Weibull slider manipulation, despite users not identifying slider parameters themselves. Our work stresses the benefit of the Weibull distribution and significance of image purpose in underwater image enhancement. |
format | Online Article Text |
id | pubmed-10098941 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-100989412023-04-14 Weibull Tone Mapping (WTM) for the Enhancement of Underwater Imagery Game, Chloe Amanda Thompson, Michael Barry Finlayson, Graham David Sensors (Basel) Article Domain experts prefer interactive and targeted control-point tone mapping operations (TMOs) to enhance underwater image quality and feature visibility; though this comes at the expense of time and training. In this paper, we provide end-users with a simpler and faster interactive tone-mapping approach. This is built upon Weibull Tone Mapping (WTM) theory; introduced in previous work as a preferred tool to describe and improve domain expert TMOs. We allow end-users to easily shape brightness distributions according to the Weibull distribution, using two parameter sliders which modify the distribution peak and spread. Our experiments showed that 10 domain experts found the two-slider Weibull manipulation sufficed to make a desired adjustment in >80% of images in a large dataset. For the remaining ∼20%, observers opted for a control-point TMO which can, broadly, encompass many global tone mapping algorithms. Importantly, 91% of these control-point TMOs can actually be visually well-approximated by our Weibull slider manipulation, despite users not identifying slider parameters themselves. Our work stresses the benefit of the Weibull distribution and significance of image purpose in underwater image enhancement. MDPI 2023-03-28 /pmc/articles/PMC10098941/ /pubmed/37050592 http://dx.doi.org/10.3390/s23073533 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Game, Chloe Amanda Thompson, Michael Barry Finlayson, Graham David Weibull Tone Mapping (WTM) for the Enhancement of Underwater Imagery |
title | Weibull Tone Mapping (WTM) for the Enhancement of Underwater Imagery |
title_full | Weibull Tone Mapping (WTM) for the Enhancement of Underwater Imagery |
title_fullStr | Weibull Tone Mapping (WTM) for the Enhancement of Underwater Imagery |
title_full_unstemmed | Weibull Tone Mapping (WTM) for the Enhancement of Underwater Imagery |
title_short | Weibull Tone Mapping (WTM) for the Enhancement of Underwater Imagery |
title_sort | weibull tone mapping (wtm) for the enhancement of underwater imagery |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10098941/ https://www.ncbi.nlm.nih.gov/pubmed/37050592 http://dx.doi.org/10.3390/s23073533 |
work_keys_str_mv | AT gamechloeamanda weibulltonemappingwtmfortheenhancementofunderwaterimagery AT thompsonmichaelbarry weibulltonemappingwtmfortheenhancementofunderwaterimagery AT finlaysongrahamdavid weibulltonemappingwtmfortheenhancementofunderwaterimagery |