FIN-PRINT a fully-automated multi-stage deep-learning-based framework for the individual recognition of killer whales
Abstract Biometric identification techniques such as photo-identification require an array of unique natural markings to identify individuals. From 1975 to present, Bigg’s killer whales have been photo-identified along the west coast of North America, resulting in one of the largest and longest-runn...
Published in: | Scientific Reports |
---|---|
Main Authors: | , , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Nature Portfolio
2021
|
Subjects: | |
Online Access: | https://doi.org/10.1038/s41598-021-02506-6 https://doaj.org/article/4ecef3fe909b418faa81cc9325e6d26c |
id |
ftdoajarticles:oai:doaj.org/article:4ecef3fe909b418faa81cc9325e6d26c |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:4ecef3fe909b418faa81cc9325e6d26c 2023-05-15T17:03:28+02:00 FIN-PRINT a fully-automated multi-stage deep-learning-based framework for the individual recognition of killer whales Christian Bergler Alexander Gebhard Jared R. Towers Leonid Butyrev Gary J. Sutton Tasli J. H. Shaw Andreas Maier Elmar Nöth 2021-12-01T00:00:00Z https://doi.org/10.1038/s41598-021-02506-6 https://doaj.org/article/4ecef3fe909b418faa81cc9325e6d26c EN eng Nature Portfolio https://doi.org/10.1038/s41598-021-02506-6 https://doaj.org/toc/2045-2322 doi:10.1038/s41598-021-02506-6 2045-2322 https://doaj.org/article/4ecef3fe909b418faa81cc9325e6d26c Scientific Reports, Vol 11, Iss 1, Pp 1-16 (2021) Medicine R Science Q article 2021 ftdoajarticles https://doi.org/10.1038/s41598-021-02506-6 2022-12-31T07:46:11Z Abstract Biometric identification techniques such as photo-identification require an array of unique natural markings to identify individuals. From 1975 to present, Bigg’s killer whales have been photo-identified along the west coast of North America, resulting in one of the largest and longest-running cetacean photo-identification datasets. However, data maintenance and analysis are extremely time and resource consuming. This study transfers the procedure of killer whale image identification into a fully automated, multi-stage, deep learning framework, entitled FIN-PRINT. It is composed of multiple sequentially ordered sub-components. FIN-PRINT is trained and evaluated on a dataset collected over an 8-year period (2011–2018) in the coastal waters off western North America, including 121,000 human-annotated identification images of Bigg’s killer whales. At first, object detection is performed to identify unique killer whale markings, resulting in 94.4% recall, 94.1% precision, and 93.4% mean-average-precision (mAP). Second, all previously identified natural killer whale markings are extracted. The third step introduces a data enhancement mechanism by filtering between valid and invalid markings from previous processing levels, achieving 92.8% recall, 97.5%, precision, and 95.2% accuracy. The fourth and final step involves multi-class individual recognition. When evaluated on the network test set, it achieved an accuracy of 92.5% with 97.2% top-3 unweighted accuracy (TUA) for the 100 most commonly photo-identified killer whales. Additionally, the method achieved an accuracy of 84.5% and a TUA of 92.9% when applied to the entire 2018 image collection of the 100 most common killer whales. The source code of FIN-PRINT can be adapted to other species and will be publicly available. Article in Journal/Newspaper Killer Whale Killer whale Directory of Open Access Journals: DOAJ Articles Scientific Reports 11 1 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Medicine R Science Q |
spellingShingle |
Medicine R Science Q Christian Bergler Alexander Gebhard Jared R. Towers Leonid Butyrev Gary J. Sutton Tasli J. H. Shaw Andreas Maier Elmar Nöth FIN-PRINT a fully-automated multi-stage deep-learning-based framework for the individual recognition of killer whales |
topic_facet |
Medicine R Science Q |
description |
Abstract Biometric identification techniques such as photo-identification require an array of unique natural markings to identify individuals. From 1975 to present, Bigg’s killer whales have been photo-identified along the west coast of North America, resulting in one of the largest and longest-running cetacean photo-identification datasets. However, data maintenance and analysis are extremely time and resource consuming. This study transfers the procedure of killer whale image identification into a fully automated, multi-stage, deep learning framework, entitled FIN-PRINT. It is composed of multiple sequentially ordered sub-components. FIN-PRINT is trained and evaluated on a dataset collected over an 8-year period (2011–2018) in the coastal waters off western North America, including 121,000 human-annotated identification images of Bigg’s killer whales. At first, object detection is performed to identify unique killer whale markings, resulting in 94.4% recall, 94.1% precision, and 93.4% mean-average-precision (mAP). Second, all previously identified natural killer whale markings are extracted. The third step introduces a data enhancement mechanism by filtering between valid and invalid markings from previous processing levels, achieving 92.8% recall, 97.5%, precision, and 95.2% accuracy. The fourth and final step involves multi-class individual recognition. When evaluated on the network test set, it achieved an accuracy of 92.5% with 97.2% top-3 unweighted accuracy (TUA) for the 100 most commonly photo-identified killer whales. Additionally, the method achieved an accuracy of 84.5% and a TUA of 92.9% when applied to the entire 2018 image collection of the 100 most common killer whales. The source code of FIN-PRINT can be adapted to other species and will be publicly available. |
format |
Article in Journal/Newspaper |
author |
Christian Bergler Alexander Gebhard Jared R. Towers Leonid Butyrev Gary J. Sutton Tasli J. H. Shaw Andreas Maier Elmar Nöth |
author_facet |
Christian Bergler Alexander Gebhard Jared R. Towers Leonid Butyrev Gary J. Sutton Tasli J. H. Shaw Andreas Maier Elmar Nöth |
author_sort |
Christian Bergler |
title |
FIN-PRINT a fully-automated multi-stage deep-learning-based framework for the individual recognition of killer whales |
title_short |
FIN-PRINT a fully-automated multi-stage deep-learning-based framework for the individual recognition of killer whales |
title_full |
FIN-PRINT a fully-automated multi-stage deep-learning-based framework for the individual recognition of killer whales |
title_fullStr |
FIN-PRINT a fully-automated multi-stage deep-learning-based framework for the individual recognition of killer whales |
title_full_unstemmed |
FIN-PRINT a fully-automated multi-stage deep-learning-based framework for the individual recognition of killer whales |
title_sort |
fin-print a fully-automated multi-stage deep-learning-based framework for the individual recognition of killer whales |
publisher |
Nature Portfolio |
publishDate |
2021 |
url |
https://doi.org/10.1038/s41598-021-02506-6 https://doaj.org/article/4ecef3fe909b418faa81cc9325e6d26c |
genre |
Killer Whale Killer whale |
genre_facet |
Killer Whale Killer whale |
op_source |
Scientific Reports, Vol 11, Iss 1, Pp 1-16 (2021) |
op_relation |
https://doi.org/10.1038/s41598-021-02506-6 https://doaj.org/toc/2045-2322 doi:10.1038/s41598-021-02506-6 2045-2322 https://doaj.org/article/4ecef3fe909b418faa81cc9325e6d26c |
op_doi |
https://doi.org/10.1038/s41598-021-02506-6 |
container_title |
Scientific Reports |
container_volume |
11 |
container_issue |
1 |
_version_ |
1766057336250564608 |