SEALNET: Facial recognition software for ecological studies of harbor seals
Abstract Methods for long‐term monitoring of coastal species such as harbor seals (Phoca vitulina) are often costly, time‐consuming, and highly invasive, underscoring the need for improved techniques for data collection and analysis. Here, we propose the use of automated facial recognition technolog...
Published in: | Ecology and Evolution |
---|---|
Main Authors: | , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Wiley
2022
|
Subjects: | |
Online Access: | https://doi.org/10.1002/ece3.8851 https://doaj.org/article/d63739f6a59143b8aaf3d4c42011433f |
id |
ftdoajarticles:oai:doaj.org/article:d63739f6a59143b8aaf3d4c42011433f |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:d63739f6a59143b8aaf3d4c42011433f 2023-05-15T17:58:56+02:00 SEALNET: Facial recognition software for ecological studies of harbor seals Zach Birenbaum Hieu Do Lauren Horstmyer Hailey Orff Krista Ingram Ahmet Ay 2022-05-01T00:00:00Z https://doi.org/10.1002/ece3.8851 https://doaj.org/article/d63739f6a59143b8aaf3d4c42011433f EN eng Wiley https://doi.org/10.1002/ece3.8851 https://doaj.org/toc/2045-7758 2045-7758 doi:10.1002/ece3.8851 https://doaj.org/article/d63739f6a59143b8aaf3d4c42011433f Ecology and Evolution, Vol 12, Iss 5, Pp n/a-n/a (2022) Ecology QH540-549.5 article 2022 ftdoajarticles https://doi.org/10.1002/ece3.8851 2022-12-31T02:51:02Z Abstract Methods for long‐term monitoring of coastal species such as harbor seals (Phoca vitulina) are often costly, time‐consuming, and highly invasive, underscoring the need for improved techniques for data collection and analysis. Here, we propose the use of automated facial recognition technology for identification of individual seals and demonstrate its utility in ecological and population studies. We created a software package, SealNet, that automates photo identification of seals, using a graphical user interface (GUI) software to detect, align, and chip seal faces from photographs and a deep convolutional neural network (CNN) suitable for small datasets (e.g., 100 seals with five photos per seal) to classify individual seals. We piloted the SealNet technology with a population of harbor seals located within Casco Bay on the coast of Maine, USA. Across two years of sampling, 2019 and 2020, at seven haul‐out sites in Middle Bay, we obtained a dataset optimized for the development and testing of SealNet. We processed 1752 images representing 408 individual seals and achieved 88% Rank‐1 and 96% Rank‐5 accuracy in closed set seal identification. In identifying individual seals, SealNet software outperformed a similar face recognition method, PrimNet, developed for primates but retrained on seals. The ease and wealth of image data that can be processed using SealNet software contributes a vital tool for ecological and behavioral studies of marine mammals in the developing field of conservation technology. Article in Journal/Newspaper Phoca vitulina Directory of Open Access Journals: DOAJ Articles Middle Bay ENVELOPE(-57.495,-57.495,51.465,51.465) Ecology and Evolution 12 5 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Ecology QH540-549.5 |
spellingShingle |
Ecology QH540-549.5 Zach Birenbaum Hieu Do Lauren Horstmyer Hailey Orff Krista Ingram Ahmet Ay SEALNET: Facial recognition software for ecological studies of harbor seals |
topic_facet |
Ecology QH540-549.5 |
description |
Abstract Methods for long‐term monitoring of coastal species such as harbor seals (Phoca vitulina) are often costly, time‐consuming, and highly invasive, underscoring the need for improved techniques for data collection and analysis. Here, we propose the use of automated facial recognition technology for identification of individual seals and demonstrate its utility in ecological and population studies. We created a software package, SealNet, that automates photo identification of seals, using a graphical user interface (GUI) software to detect, align, and chip seal faces from photographs and a deep convolutional neural network (CNN) suitable for small datasets (e.g., 100 seals with five photos per seal) to classify individual seals. We piloted the SealNet technology with a population of harbor seals located within Casco Bay on the coast of Maine, USA. Across two years of sampling, 2019 and 2020, at seven haul‐out sites in Middle Bay, we obtained a dataset optimized for the development and testing of SealNet. We processed 1752 images representing 408 individual seals and achieved 88% Rank‐1 and 96% Rank‐5 accuracy in closed set seal identification. In identifying individual seals, SealNet software outperformed a similar face recognition method, PrimNet, developed for primates but retrained on seals. The ease and wealth of image data that can be processed using SealNet software contributes a vital tool for ecological and behavioral studies of marine mammals in the developing field of conservation technology. |
format |
Article in Journal/Newspaper |
author |
Zach Birenbaum Hieu Do Lauren Horstmyer Hailey Orff Krista Ingram Ahmet Ay |
author_facet |
Zach Birenbaum Hieu Do Lauren Horstmyer Hailey Orff Krista Ingram Ahmet Ay |
author_sort |
Zach Birenbaum |
title |
SEALNET: Facial recognition software for ecological studies of harbor seals |
title_short |
SEALNET: Facial recognition software for ecological studies of harbor seals |
title_full |
SEALNET: Facial recognition software for ecological studies of harbor seals |
title_fullStr |
SEALNET: Facial recognition software for ecological studies of harbor seals |
title_full_unstemmed |
SEALNET: Facial recognition software for ecological studies of harbor seals |
title_sort |
sealnet: facial recognition software for ecological studies of harbor seals |
publisher |
Wiley |
publishDate |
2022 |
url |
https://doi.org/10.1002/ece3.8851 https://doaj.org/article/d63739f6a59143b8aaf3d4c42011433f |
long_lat |
ENVELOPE(-57.495,-57.495,51.465,51.465) |
geographic |
Middle Bay |
geographic_facet |
Middle Bay |
genre |
Phoca vitulina |
genre_facet |
Phoca vitulina |
op_source |
Ecology and Evolution, Vol 12, Iss 5, Pp n/a-n/a (2022) |
op_relation |
https://doi.org/10.1002/ece3.8851 https://doaj.org/toc/2045-7758 2045-7758 doi:10.1002/ece3.8851 https://doaj.org/article/d63739f6a59143b8aaf3d4c42011433f |
op_doi |
https://doi.org/10.1002/ece3.8851 |
container_title |
Ecology and Evolution |
container_volume |
12 |
container_issue |
5 |
_version_ |
1766167664582983680 |