The DOI matches its Crossref record; 49 of the 49 references it cites were found in a registry or an index.
Deep learning‐based methods for individual recognition in small birds
Open accessPublished version of a preprint
Abstract
Individual identification is a crucial step to answer many questions in evolutionary biology and is mostly performed by marking animals with tags. Such methods are well‐established, but often make data collection and analyses time‐consuming, or limit the contexts in which data can be collected. Recent computational advances, specifically deep learning, can help overcome the limitations of collecting large‐scale data across contexts. However, one of the bottlenecks preventing the application of deep learning for individual identification is the need to collect and identify hundreds to thousands of individually labelled pictures to train convolutional neural networks (CNNs). Here we describe procedures for automating the collection of training data, generating training datasets, and training CNNs to allow identification of individual birds. We apply our procedures to three small bird species, the sociable weaver Philetairus socius, the great tit Parus major and the zebra finch Taeniopygia guttata , representing both wild and captive contexts. We first show how the collection of individually labelled images can be automated, allowing the construction of training datasets consisting of hundreds of images per individual. Second, we describe how to train a CNN to uniquely re‐identify each individual in new images. Third, we illustrate the general applicability of CNNs for studies in animal biology by showing that trained CNNs can re‐identify individual birds in images collected in contexts that differ from the ones originally used to train the CNNs. Finally, we present a potential solution to solve the issues of new incoming individuals. Overall, our work demonstrates the feasibility of applying state‐of‐the‐art deep learning tools for individual identification of birds, both in the laboratory and in the wild. These techniques are made possible by our approaches that allow efficient collection of training data. The ability to conduct individual recognition of birds without requiring external markers that can be visually identified by human observers represents a major advance over current methods.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“More recently, artificial intelligence deep learning models, such as Convolutional Neural Networks (CNN), have been developed to identify birds, bats or amphibians36–40.”
From Soundscapes and deep learning enable tracking biodiversity recovery in tropical forests (2023) · cites this paper as [37]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 1×
“We used the VGG19 convolutional neural network architecture (Simonyan & Zisserman, 2014) and the weights of a network pre-trained on the ImageNet dataset (a dataset with more than 14 million pictures and 20000 classes, Deng et al., 2009).”
MethodAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
A Mathematical Theory of Communication
Shannon, C. E. (1948) · Bell System Technical Journal · doi:10.1002/j.1538-7305.1948.tb01338.x · Cited by 88,486
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 2×
“We used the VGG19 convolutional neural network architecture (Simonyan & Zisserman, 2014) and the weights of a network pre-trained on the ImageNet dataset (a dataset with more than 14 million pictures and 20000 classes, Deng et al., 2009).”
MethodNIH Image to ImageJ: 25 years of image analysis
Schneider, C. A., Rasband, W. S., & Eliceiri, K. W. (2012) · Nature Methods · doi:10.1038/nmeth.2089 · Cited by 64,638
Image quality assessment: from error visibility to structural similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.819861 · Cited by 57,892
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
(2014) · Cited by 33,419
He, K., Gkioxari, G., Dollar, P., & Girshick, R. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.322 · Cited by 29,137
FaceNet: A unified embedding for face recognition and clustering
Schroff, F., Kalenichenko, D., & Philbin, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298682 · Cited by 15,267
Chandola, V., Banerjee, A., & Kumar, V. (2009) · ACM Computing Surveys · doi:10.1145/1541880.1541882 · Cited by 11,687
Machine learning: Trends, perspectives, and prospects
Jordan, M. I., & Mitchell, T. M. (2015) · Science · doi:10.1126/science.aaa8415 · Cited by 9,955
A systematic study of the class imbalance problem in convolutional neural networks
Buda, M., Maki, A., & Mazurowski, M. A. (2018) · Neural Networks · doi:10.1016/j.neunet.2018.07.011 · Cited by 3,088
Survey on deep learning with class imbalance
Johnson, J. M., & Khoshgoftaar, T. M. (2019) · Journal of Big Data · doi:10.1186/s40537-019-0192-5 · Cited by 3,032
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W. F., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvprw.2009.5206848 · Cited by 2,714
Pimentel, M. A. F., Clifton, D. A., Clifton, L., & Tarassenko, L. (2014) · Signal Processing · doi:10.1016/j.sigpro.2013.12.026 · Cited by 1,649 · cited 1×
“Such a problem fits in the anomaly (Chandola, Banerjee, & Kumar, 2009) and novelty (Pimentel, Clifton, Clifton, & Tarassenko, 2014) detection domain.”
BackgroundDeep learning for computational biology
Angermueller, C., Pärnamaa, T., Parts, L., & Stegle, O. (2016) · Molecular Systems Biology · doi:10.15252/msb.20156651 · Cited by 1,473 · cited 1×
“…hand-crafted feature extraction, automatically learn from the data the features that are optimal for solving a given classification problem (see Angermueller, Pärnamaa, Parts, & Stegle, 2016; Christin et al., 2019; Jordan & Mitchell, 2015; LeCun, Bengio, & Hinton, 2015 for a detailed…”
MethodNorouzzadeh, M. S., Nguyen, A., Kosmala, M., Swanson, A., Palmer, M. S., Packer, C., & Clune, J. (2018) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1719367115 · Cited by 1,230
Clutton-Brock, T. H., & Sheldon, B. C. (2010) · Trends in Ecology & Evolution · doi:10.1016/j.tree.2010.08.002 · Cited by 977 · cited 1×
“Beyond species recognition, another promising application of CNNs is individual identification, which is crucial to many studies in ecology, behaviour and conservation (Clutton-Brock & Sheldon, 2010).”
BackgroundRevisiting Small Batch Training for Deep Neural NetworksPreprint
Masters, D. A., & Luschi, C. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.07612 · Cited by 945
Deep Learning: A Critical Appraisal
Marcus, G. (2018) · arXiv · doi:10.48550/arxiv.1801.00631 · Cited by 853
Lopes, A. T., de Aguiar, E., De Souza, A. F., & Oliveira-Santos, T. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2016.07.026 · Cited by 799
idTracker: tracking individuals in a group by automatic identification of unmarked animals
Pérez‐Escudero, A., Vicente-Page, J., Hinz, R. C., Arganda, S., & de Polavieja, G. G. (2014) · Nature Methods · doi:10.1038/nmeth.2994 · Cited by 775
Gated Siamese Convolutional Neural Network Architecture for Human Re-identification
Varior, R. R., Haloi, M., & Wang, G. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46484-8_48 · Cited by 748
Applications for deep learning in ecology
Christin, S., Hervet, É., & Lecomte, N. (2019) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.13256 · Cited by 724
Experimentally induced innovations lead to persistent culture via conformity in wild birds
Aplin, L. M., Farine, D. R., Morand‐Ferron, J., Cockburn, A., Thornton, A., & Sheldon, B. C. (2014) · Nature · doi:10.1038/nature13998 · Cited by 701
Self-citationMachine learning to classify animal species in camera trap images: Applications in ecology
Tabak, M. A., Norouzzadeh, M. S., Wolfson, D. W., Sweeney, S. J., Vercauteren, K. C., Snow, N. P., Halseth, J. M., Di Salvo, P. A., Lewis, J. S., White, M. D., et al. (2019) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.13120 · Cited by 504 · cited 1×
“This and other examples (e.g. Rzanny, Seeland, Wäldchen & Mäder, 2017; Tabak et al., 2019) highlight the potentialities of deep learning for reducing human effort and increasing identification performance.”
BackgroundA computer vision for animal ecology
Weinstein, B. G. (2017) · Journal of Animal Ecology · doi:10.1111/1365-2656.12780 · Cited by 457 · cited 1×
“However, relying on 86 humans for individual identification and data collection is extremely time-consuming 87 (Weinstein, 2018).”
Backgroundidtracker.ai: tracking all individuals in small or large collectives of unmarked animals
Romero-Ferrero, F., Bergomi, M. G., Hinz, R. C., Heras, F. J. H., & de Polavieja, G. G. (2019) · Nature Methods · doi:10.1038/s41592-018-0295-5 · Cited by 432
Towards on-farm pig face recognition using convolutional neural networks
Hansen, M., Smith, M. L., Smith, L. N., Salter, M. G., Baxter, E., Farish, M., & Grieve, B. (2018) · Computers in Industry · doi:10.1016/j.compind.2018.02.016 · Cited by 345 · cited 10×
“(2018) 66 used a long term database of more than 3 million labelled pictures to train a CNN to 67 automatically recognize 48 African animal species.”
BackgroundMethodInfluentialReality mining of animal social systems
Krause, J., Krause, S., Arlinghaus, R., Psorakis, I., Roberts, S., & Rutz, C. (2013) · Trends in Ecology & Evolution · doi:10.1016/j.tree.2013.06.002 · Cited by 269
Schneider, S., Taylor, G. W., Linquist, S., & Kremer, S. C. (2019) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.13133 · Cited by 245
Chimpanzee face recognition from videos in the wild using deep learning
Schofield, D., Nagrani, A., Zisserman, A., Hayashi, M., Matsuzawa, T., Biro, D., & Carvalho, S. (2019) · Science Advances · doi:10.1126/sciadv.aaw0736 · Cited by 224 · cited 1×
“More recently, a handful of studies have applied the similar methods to other animal species, allowing computers to individually recognize primates (Deb et al., 2018; Schofield et al., 2019), pigs (Hansen et al., 2018) and elephants (Körschens, Barz, & Denzler, 2018).”
BackgroundDeep Learning for Understanding Faces: Machines May Be Just as Good, or Better, than Humans
Ranjan, R., Sankaranarayanan, S., Bansal, A., Bodla, N., Chen, J.-C., Patel, V. M., Castillo, C. D., & Chellappa, R. (2018) · IEEE Signal Processing Magazine · doi:10.1109/msp.2017.2764116 · Cited by 199
Examining the Impact of Blur on Recognition by Convolutional NetworksPreprint
Vasiljevic, I., Chakrabarti, A., & Shakhnarovich, G. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.05760 · Cited by 197
The VGG Image Annotator (VIA).Preprint
Dutta, A., & Zisserman, A. (2019) · arXiv (Cornell University) · Cited by 166
Davis, G. H., Crofoot, M. C., & Farine, D. R. (2018) · Animal Behaviour · doi:10.1016/j.anbehav.2018.04.012 · Cited by 140
Self-citationCovas, R., Plessis, M. A. D., & Doutrelant, C. (2008) · Behavioral Ecology and Sociobiology · doi:10.1007/s00265-008-0640-2 · Cited by 128
Self-citationRzanny, M., Seeland, M., Wäldchen, J., & Mäder, P. (2017) · Plant Methods · doi:10.1186/s13007-017-0245-8 · Cited by 108
Face Recognition: Primates in the Wild
Deb, D., Wiper, S., Gong, S., Shi, Y., Tymoszek, C., Fletcher, A., & Jain, A. K. (2018) · IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS) · doi:10.1109/btas.2018.8698538 · Cited by 96
Deriving Animal Behaviour from High-Frequency GPS: Tracking Cows in Open and Forested Habitat
de Weerd, N., van Langevelde, F., van Oeveren, H., Nolet, B. A., Kölzsch, A., Prins, H. H. T., & de Boer, W. F. (2015) · PLoS ONE · doi:10.1371/journal.pone.0129030 · Cited by 85
An automated barcode tracking system for behavioural studies in birds
Alarcón‐Nieto, G., Graving, J. M., Klarevas‐Irby, J. A., Maldonado‐Chaparro, A. A., Mueller, I., & Farine, D. R. (2018) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.13005 · Cited by 83
Self-citationEstimating uncertainty and reliability of social network data using Bayesian inference
Farine, D. R., & Strandburg‐Peshkin, A. (2015) · Royal Society Open Science · doi:10.1098/rsos.150367 · Cited by 76 · cited 1×
“…in other studies it may be more costly to have misidentified individuals For example, misidentifi-cations are very costly when constructing social networks (Davis, Crofoot, & Farine, 2018), while at the same time social networks are very identification hungry (Farine & Strandburg-Peshkin, 2015).”
BackgroundSelf-citationTraining a Convolutional Neural Network for Appearance-Invariant Place RecognitionPreprint
Gomez-Ojeda, R., López-Antequera, M., Petkov, N., & González-Jiménez, J. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1505.07428 · Cited by 56 · cited 1×
“The problem of long-term application of neural network algorithms has been studied in the context of place recognition (e.g. streets recognitions; Gomez-Ojeda et al., 2015); however, to our knowledge, there is still no study addressing the impact of changes in appearance in animals in deep…”
BackgroundLevin, I. I., Zonana, D. M., Burt, J. M., & Safran, R. J. (2015) · PLoS ONE · doi:10.1371/journal.pone.0137242 · Cited by 38
Irreproducible text-book “knowledge”: The effects of color bands on zebra finch fitness
Wang, D., Forstmeier, W., Ihle, M., Khadraoui, M., Jerónimo, S., Martin, K., & Kempenaers, B. (2018) · Evolution · doi:10.1111/evo.13459 · Cited by 30
Towards Automatic Identification of Elephants in the WildPreprint
Körschens, M., Barz, B., & Denzler, J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.04418 · Cited by 27
Research works printed but not linked: 3
- Ferreira A. C., 2020, AndreCFerreira/Bird_individualID: Bird_individualID (version 1.0), Zenodo
- Huang G. B. Ramesh M. Berg T. &Learned‐Miller E.(2007).Labeled faces in the wild: A database for studying face recognition in unconstrained environments.Technical Report(pp.7–49).Amherst MA:University of Massachusetts.
- Sünderhauf N., 2013, Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Workshop on Long‐Term Autonomy
Cited by
Sorted by citations
Machine learning and deep learning—A review for ecologists
Pichler, M., & Hartig, F. (2023) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.14061 · Cited by 576
“…et al., 2019; Guirado et al., 2018; Torney et al., 2019 ) or camera (trap) images (Aodha et al., 2018 ; Beery et al., 2020; Fairbrass et al., 2018 ; Ferreira et al., 2020 ; Fritzler et al., 2017; Lasseck, 2018 ; Mäder et al., 2021; Norouzzadeh et al., 2021; Stowell et al., 2018 ; Tabak et al.,…”
BackgroundMethodInfluentialDeep learning as a tool for ecology and evolution
Borowiec, M. L., Dikow, R. B., Frandsen, P. B., McKeeken, A. J., Valentini, G., & White, A. E. (2022) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.13901 · Cited by 295
“Usually based on the use of CNNs for image recognition, deep learning can also be combined with other technologies (e.g. motion sensors, RFID) to develop automated data-processing pipelines to collect and label samples, as was done by Ferreira et al. (2020) for three different bird species.”
BackgroundBroad‐scale applications of the Raspberry Pi: A review and guide for biologists
Jolles, J. W. (2021) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.13652 · Cited by 240
“Youngblood (2020) set up bird-feeders with RFID-readers for the remote monitoring of wild bird populations, while Ferreira et al. (2020) used an RFID-equipped birdfeeder to automatically generate a large labelled dataset of bird photos for machine learning.”
BackgroundDuporge, I., Isupova, O., Reece, S., Macdonald, D. W., & Wang, T. (2020) · Remote Sensing in Ecology and Conservation · doi:10.1002/rse2.195 · Cited by 173
“camera trap images, aerial survey images, and unmanned aerial vehicle (UAV) images [43-48].”
BackgroundUnlocking the potential of deep learning for marine ecology: overview, applications, and outlook
Goodwin, M., Halvorsen, K. T., Jiao, L., Knausgård, K. M., Martin, A. H., Moyano, M., Oomen, R. A., Rasmussen, J. H., Sørdalen, T. K., & Thorbjørnsen, S. H. (2021) · ICES Journal of Marine Science · doi:10.1093/icesjms/fsab255 · Cited by 157
Metadata
- Authors
- Ferreira, A. C., Silva, L. R., Renna, F., Brandl, H. B., Renoult, J. P., Farine, D. R., Covas, R., & Doutrelant, C.
- Affiliations
- Centre National de la Recherche Scientifique (FR)
- Universidade do Porto (PT)
- University of Konstanz (DE)
- University of Cape Town (ZA)
- Corresponding author
- Ferreira, André C.
- ORCID
- Venue
- Methods in Ecology and Evolution
- Publisher
- Wiley
- Published
- 2020-07-26
- Volume
- 11
- Issue
- 9
- Pages
- 1072-1085
- ISSN
- 2041-210X (ISSN-L)
- OpenAlex
- W3038699438
- Cited by
- 203
- References
- 47
- Citations by year
- 2026: 15 · 2025: 38 · 2024: 43 · 2023: 39 · 2022: 27 · 2021: 35 · 2020: 6
- FWCI
- 10.40
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Methods in Ecology and Evolution (publishedVersion, cc-by)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc-nd)
- HAL (submittedVersion, cc-by)
- KOPS (University of Konstanz) (submittedVersion)
- KOPS (University of Konstanz) (submittedVersion, cc-by)
- MPG.PuRe (Max Planck Society) (submittedVersion)
- Funders
- Max-Planck-Gesellschaft
- Fundação para a Ciência e a Tecnologia (CEECIND/01970/2017, IF/01411/2014/CP1256/CT0007, PTDC/BIA‐EVF/5249/201, SFRH/BD/122106/2016)
- Agence Nationale de la Recherche (ANR‐ 15‐CE32‐0012‐02, ANR 19‐CE02‐0014‐02)
- Deutsche Forschungsgemeinschaft (FA 1402/4‐1, 422037984)
- University of Cape Town
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Life Sciences › Agricultural and Biological Sciences › Plant Science › Smart Agriculture and AI
- Keywords
- individual recognition, small birds, convolutional neural networks, sociable weaver, Parus major, zebra finch, re-identification
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
