A real‐world dataset and data simulation algorithm for automated fish species identification
Abstract Developing high‐performing machine learning algorithms requires large amounts of annotated data. Manual annotation of data is labour‐intensive, and the cost and effort needed are an important obstacle to the development and deployment of automated analysis. In a previous work, we have shown...
Published in: | Geoscience Data Journal |
---|---|
Main Authors: | , , , |
Other Authors: | |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Wiley
2021
|
Subjects: | |
Online Access: | http://dx.doi.org/10.1002/gdj3.114 https://onlinelibrary.wiley.com/doi/pdf/10.1002/gdj3.114 https://onlinelibrary.wiley.com/doi/full-xml/10.1002/gdj3.114 https://rmets.onlinelibrary.wiley.com/doi/pdf/10.1002/gdj3.114 |
id |
crwiley:10.1002/gdj3.114 |
---|---|
record_format |
openpolar |
spelling |
crwiley:10.1002/gdj3.114 2024-09-15T18:25:23+00:00 A real‐world dataset and data simulation algorithm for automated fish species identification Allken, Vaneeda Rosen, Shale Handegard, Nils Olav Malde, Ketil Norges Forskningsråd 2021 http://dx.doi.org/10.1002/gdj3.114 https://onlinelibrary.wiley.com/doi/pdf/10.1002/gdj3.114 https://onlinelibrary.wiley.com/doi/full-xml/10.1002/gdj3.114 https://rmets.onlinelibrary.wiley.com/doi/pdf/10.1002/gdj3.114 en eng Wiley http://creativecommons.org/licenses/by/4.0/ Geoscience Data Journal volume 8, issue 2, page 199-209 ISSN 2049-6060 2049-6060 journal-article 2021 crwiley https://doi.org/10.1002/gdj3.114 2024-07-30T04:17:26Z Abstract Developing high‐performing machine learning algorithms requires large amounts of annotated data. Manual annotation of data is labour‐intensive, and the cost and effort needed are an important obstacle to the development and deployment of automated analysis. In a previous work, we have shown that deep learning classifiers can successfully be trained on synthetic images and annotations. Here, we provide a curated set of fish image data and backgrounds, the necessary software tools to generate synthetic images and annotations, and annotated real datasets to test classifier performance. The dataset is constructed from images collected using the Deep Vision system during two surveys from 2017 and 2018 that targeted economically important pelagic species in the Northeast Atlantic Ocean. We annotated a total of 1,879 images, randomly selected across trawl stations from both surveys, comprising 482 images of blue whiting, 456 images of Atlantic herring, 341 images of Atlantic mackerel, 335 images of mesopelagic fishes and 265 images containing a mixture of the four categories. Article in Journal/Newspaper Northeast Atlantic Wiley Online Library Geoscience Data Journal 8 2 199 209 |
institution |
Open Polar |
collection |
Wiley Online Library |
op_collection_id |
crwiley |
language |
English |
description |
Abstract Developing high‐performing machine learning algorithms requires large amounts of annotated data. Manual annotation of data is labour‐intensive, and the cost and effort needed are an important obstacle to the development and deployment of automated analysis. In a previous work, we have shown that deep learning classifiers can successfully be trained on synthetic images and annotations. Here, we provide a curated set of fish image data and backgrounds, the necessary software tools to generate synthetic images and annotations, and annotated real datasets to test classifier performance. The dataset is constructed from images collected using the Deep Vision system during two surveys from 2017 and 2018 that targeted economically important pelagic species in the Northeast Atlantic Ocean. We annotated a total of 1,879 images, randomly selected across trawl stations from both surveys, comprising 482 images of blue whiting, 456 images of Atlantic herring, 341 images of Atlantic mackerel, 335 images of mesopelagic fishes and 265 images containing a mixture of the four categories. |
author2 |
Norges Forskningsråd |
format |
Article in Journal/Newspaper |
author |
Allken, Vaneeda Rosen, Shale Handegard, Nils Olav Malde, Ketil |
spellingShingle |
Allken, Vaneeda Rosen, Shale Handegard, Nils Olav Malde, Ketil A real‐world dataset and data simulation algorithm for automated fish species identification |
author_facet |
Allken, Vaneeda Rosen, Shale Handegard, Nils Olav Malde, Ketil |
author_sort |
Allken, Vaneeda |
title |
A real‐world dataset and data simulation algorithm for automated fish species identification |
title_short |
A real‐world dataset and data simulation algorithm for automated fish species identification |
title_full |
A real‐world dataset and data simulation algorithm for automated fish species identification |
title_fullStr |
A real‐world dataset and data simulation algorithm for automated fish species identification |
title_full_unstemmed |
A real‐world dataset and data simulation algorithm for automated fish species identification |
title_sort |
real‐world dataset and data simulation algorithm for automated fish species identification |
publisher |
Wiley |
publishDate |
2021 |
url |
http://dx.doi.org/10.1002/gdj3.114 https://onlinelibrary.wiley.com/doi/pdf/10.1002/gdj3.114 https://onlinelibrary.wiley.com/doi/full-xml/10.1002/gdj3.114 https://rmets.onlinelibrary.wiley.com/doi/pdf/10.1002/gdj3.114 |
genre |
Northeast Atlantic |
genre_facet |
Northeast Atlantic |
op_source |
Geoscience Data Journal volume 8, issue 2, page 199-209 ISSN 2049-6060 2049-6060 |
op_rights |
http://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.1002/gdj3.114 |
container_title |
Geoscience Data Journal |
container_volume |
8 |
container_issue |
2 |
container_start_page |
199 |
op_container_end_page |
209 |
_version_ |
1810465891115073536 |