Towards establishing an automated selection framework for underwater image enhancement methods

Athina Ilioudi; Ben J. Wolf; Azita Dabiri; Bart De Schutter

doi:10.1109/OCEANSLimerick52467.2023.10244710

Towards establishing an automated selection framework for underwater image enhancement methods

Athina Ilioudi^*, Ben J. Wolf, Azita Dabiri, Bart De Schutter

^*Corresponding author for this work

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

4 Downloads (Pure)

Abstract

The majority of computer vision architectures are developed based on the assumption of the availability of good quality data. However, this is a particularly hard requirement to achieve in underwater conditions. To address this limitation, plenty of underwater image enhancement methods have received considerable attention during the last decades, but due to the lack of a commonly accepted framework to systematically evaluate them and to determine the likely optimal one for a given image, their adoption in practice is hindered, since it is not clear which one can achieve the best results. In this paper, we propose a standardized selection framework to evaluate the quality of an underwater image and to estimate the most suitable image enhancement technique based on its impact on the image classification performance.

Original language	English
Title of host publication	Proceedings OCEANS 2023 - Limerick, OCEANS Limerick 2023
Publisher	IEEE
Number of pages	6
ISBN (Electronic)	979-8-3503-3226-1
DOIs	https://doi.org/10.1109/OCEANSLimerick52467.2023.10244710
Publication status	Published - 2023
Event	2023 OCEANS Limerick, OCEANS Limerick 2023 - Limerick, Ireland Duration: 5 Jun 2023 → 8 Jun 2023

Conference

Conference	2023 OCEANS Limerick, OCEANS Limerick 2023
Country/Territory	Ireland
City	Limerick
Period	5/06/23 → 8/06/23

Bibliographical note

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

computer vision
image processing
underwater image enhancement

Access to Document

10.1109/OCEANSLimerick52467.2023.10244710

Towards_establishing_an_automated_selection_framework_for_underwater_image_enhancement_methodsFinal published version, 1.69 MB

Cite this

@inproceedings{9a69967b366e4f6abdbc9f7fc9f71c67,

title = "Towards establishing an automated selection framework for underwater image enhancement methods",

abstract = "The majority of computer vision architectures are developed based on the assumption of the availability of good quality data. However, this is a particularly hard requirement to achieve in underwater conditions. To address this limitation, plenty of underwater image enhancement methods have received considerable attention during the last decades, but due to the lack of a commonly accepted framework to systematically evaluate them and to determine the likely optimal one for a given image, their adoption in practice is hindered, since it is not clear which one can achieve the best results. In this paper, we propose a standardized selection framework to evaluate the quality of an underwater image and to estimate the most suitable image enhancement technique based on its impact on the image classification performance.",

keywords = "computer vision, image processing, underwater image enhancement",

author = "Athina Ilioudi and Wolf, {Ben J.} and Azita Dabiri and {De Schutter}, Bart",

note = "Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.; 2023 OCEANS Limerick, OCEANS Limerick 2023 ; Conference date: 05-06-2023 Through 08-06-2023",

year = "2023",

doi = "10.1109/OCEANSLimerick52467.2023.10244710",

language = "English",

booktitle = "Proceedings OCEANS 2023 - Limerick, OCEANS Limerick 2023",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - Towards establishing an automated selection framework for underwater image enhancement methods

AU - Ilioudi, Athina

AU - Wolf, Ben J.

AU - Dabiri, Azita

AU - De Schutter, Bart

N1 - Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

PY - 2023

Y1 - 2023

N2 - The majority of computer vision architectures are developed based on the assumption of the availability of good quality data. However, this is a particularly hard requirement to achieve in underwater conditions. To address this limitation, plenty of underwater image enhancement methods have received considerable attention during the last decades, but due to the lack of a commonly accepted framework to systematically evaluate them and to determine the likely optimal one for a given image, their adoption in practice is hindered, since it is not clear which one can achieve the best results. In this paper, we propose a standardized selection framework to evaluate the quality of an underwater image and to estimate the most suitable image enhancement technique based on its impact on the image classification performance.

AB - The majority of computer vision architectures are developed based on the assumption of the availability of good quality data. However, this is a particularly hard requirement to achieve in underwater conditions. To address this limitation, plenty of underwater image enhancement methods have received considerable attention during the last decades, but due to the lack of a commonly accepted framework to systematically evaluate them and to determine the likely optimal one for a given image, their adoption in practice is hindered, since it is not clear which one can achieve the best results. In this paper, we propose a standardized selection framework to evaluate the quality of an underwater image and to estimate the most suitable image enhancement technique based on its impact on the image classification performance.

KW - computer vision

KW - image processing

KW - underwater image enhancement

UR - http://www.scopus.com/inward/record.url?scp=85173677366&partnerID=8YFLogxK

U2 - 10.1109/OCEANSLimerick52467.2023.10244710

DO - 10.1109/OCEANSLimerick52467.2023.10244710

M3 - Conference contribution

AN - SCOPUS:85173677366

BT - Proceedings OCEANS 2023 - Limerick, OCEANS Limerick 2023

PB - IEEE

T2 - 2023 OCEANS Limerick, OCEANS Limerick 2023

Y2 - 5 June 2023 through 8 June 2023

ER -

Towards establishing an automated selection framework for underwater image enhancement methods

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this