Assessing the potential for deep learning and computer vision to identify bumble bee species from images

Abstract Pollinators are undergoing a global decline. Although vital to pollinator conservation and ecological research, species-level identification is expensive, time consuming, and requires specialized taxonomic training. However, deep learning and computer vision are providing ways to open this...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Brian J. Spiesman, Claudio Gratton, Richard G. Hatfield, William H. Hsu, Sarina Jepsen, Brian McCornack, Krushi Patel, Guanghui Wang
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/b66770b97f5443319c585fe634311ce8
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:b66770b97f5443319c585fe634311ce8
record_format dspace
spelling oai:doaj.org-article:b66770b97f5443319c585fe634311ce82021-12-02T18:15:09ZAssessing the potential for deep learning and computer vision to identify bumble bee species from images10.1038/s41598-021-87210-12045-2322https://doaj.org/article/b66770b97f5443319c585fe634311ce82021-04-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-87210-1https://doaj.org/toc/2045-2322Abstract Pollinators are undergoing a global decline. Although vital to pollinator conservation and ecological research, species-level identification is expensive, time consuming, and requires specialized taxonomic training. However, deep learning and computer vision are providing ways to open this methodological bottleneck through automated identification from images. Focusing on bumble bees, we compare four convolutional neural network classification models to evaluate prediction speed, accuracy, and the potential of this technology for automated bee identification. We gathered over 89,000 images of bumble bees, representing 36 species in North America, to train the ResNet, Wide ResNet, InceptionV3, and MnasNet models. Among these models, InceptionV3 presented a good balance of accuracy (91.6%) and average speed (3.34 ms). Species-level error rates were generally smaller for species represented by more training images. However, error rates also depended on the level of morphological variability among individuals within a species and similarity to other species. Continued development of this technology for automatic species identification and monitoring has the potential to be transformative for the fields of ecology and conservation. To this end, we present BeeMachine, a web application that allows anyone to use our classification model to identify bumble bees in their own images.Brian J. SpiesmanClaudio GrattonRichard G. HatfieldWilliam H. HsuSarina JepsenBrian McCornackKrushi PatelGuanghui WangNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-10 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Brian J. Spiesman
Claudio Gratton
Richard G. Hatfield
William H. Hsu
Sarina Jepsen
Brian McCornack
Krushi Patel
Guanghui Wang
Assessing the potential for deep learning and computer vision to identify bumble bee species from images
description Abstract Pollinators are undergoing a global decline. Although vital to pollinator conservation and ecological research, species-level identification is expensive, time consuming, and requires specialized taxonomic training. However, deep learning and computer vision are providing ways to open this methodological bottleneck through automated identification from images. Focusing on bumble bees, we compare four convolutional neural network classification models to evaluate prediction speed, accuracy, and the potential of this technology for automated bee identification. We gathered over 89,000 images of bumble bees, representing 36 species in North America, to train the ResNet, Wide ResNet, InceptionV3, and MnasNet models. Among these models, InceptionV3 presented a good balance of accuracy (91.6%) and average speed (3.34 ms). Species-level error rates were generally smaller for species represented by more training images. However, error rates also depended on the level of morphological variability among individuals within a species and similarity to other species. Continued development of this technology for automatic species identification and monitoring has the potential to be transformative for the fields of ecology and conservation. To this end, we present BeeMachine, a web application that allows anyone to use our classification model to identify bumble bees in their own images.
format article
author Brian J. Spiesman
Claudio Gratton
Richard G. Hatfield
William H. Hsu
Sarina Jepsen
Brian McCornack
Krushi Patel
Guanghui Wang
author_facet Brian J. Spiesman
Claudio Gratton
Richard G. Hatfield
William H. Hsu
Sarina Jepsen
Brian McCornack
Krushi Patel
Guanghui Wang
author_sort Brian J. Spiesman
title Assessing the potential for deep learning and computer vision to identify bumble bee species from images
title_short Assessing the potential for deep learning and computer vision to identify bumble bee species from images
title_full Assessing the potential for deep learning and computer vision to identify bumble bee species from images
title_fullStr Assessing the potential for deep learning and computer vision to identify bumble bee species from images
title_full_unstemmed Assessing the potential for deep learning and computer vision to identify bumble bee species from images
title_sort assessing the potential for deep learning and computer vision to identify bumble bee species from images
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/b66770b97f5443319c585fe634311ce8
work_keys_str_mv AT brianjspiesman assessingthepotentialfordeeplearningandcomputervisiontoidentifybumblebeespeciesfromimages
AT claudiogratton assessingthepotentialfordeeplearningandcomputervisiontoidentifybumblebeespeciesfromimages
AT richardghatfield assessingthepotentialfordeeplearningandcomputervisiontoidentifybumblebeespeciesfromimages
AT williamhhsu assessingthepotentialfordeeplearningandcomputervisiontoidentifybumblebeespeciesfromimages
AT sarinajepsen assessingthepotentialfordeeplearningandcomputervisiontoidentifybumblebeespeciesfromimages
AT brianmccornack assessingthepotentialfordeeplearningandcomputervisiontoidentifybumblebeespeciesfromimages
AT krushipatel assessingthepotentialfordeeplearningandcomputervisiontoidentifybumblebeespeciesfromimages
AT guanghuiwang assessingthepotentialfordeeplearningandcomputervisiontoidentifybumblebeespeciesfromimages
_version_ 1718378415577366528