Toggle Main Menu Toggle Search

Open Access padlockePrints

A deep learning approach to photo–identification demonstrates high performance on two dozen cetacean species

Lookup NU author(s): Dr Cameron Trotter

Downloads


Licence

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0).


Abstract

© 2023 The Authors. Methods in Ecology and Evolution published by John Wiley & Sons Ltd on behalf of British Ecological Society.Researchers can investigate many aspects of animal ecology through noninvasive photo–identification. Photo–identification is becoming more efficient as matching individuals between photos is increasingly automated. However, the convolutional neural network models that have facilitated this change need many training images to generalize well. As a result, they have often been developed for individual species that meet this threshold. These single-species methods might underperform, as they ignore potential similarities in identifying characteristics and the photo–identification process among species. In this paper, we introduce a multi-species photo–identification model based on a state-of-the-art method in human facial recognition, the ArcFace classification head. Our model uses two such heads to jointly classify species and identities, allowing species to share information and parameters within the network. As a demonstration, we trained this model with 50,796 images from 39 catalogues of 24 cetacean species, evaluating its predictive performance on 21,192 test images from the same catalogues. We further evaluated its predictive performance with two external catalogues entirely composed of identities that the model did not see during training. The model achieved a mean average precision (MAP) of 0.869 on the test set. Of these, 10 catalogues representing seven species achieved a MAP score over 0.95. For some species, there was notable variation in performance among catalogues, largely explained by variation in photo quality. Finally, the model appeared to generalize well, with the two external catalogues scoring similarly to their species' counterparts in the larger test set. From our cetacean application, we provide a list of recommendations for potential users of this model, focusing on those with cetacean photo–identification catalogues. For example, users with high quality images of animals identified by dorsal nicks and notches should expect near optimal performance. Users can expect decreasing performance for catalogues with higher proportions of indistinct individuals or poor quality photos. Finally, we note that this model is currently freely available as code in a GitHub repository and as a graphical user interface, with additional functionality for collaborative data management, via Happywhale.com.


Publication metadata

Author(s): Patton PT, Cheeseman T, Abe K, Yamaguchi T, Reade W, Southerland K, Howard A, Oleson EM, Allen JB, Ashe E, Athayde A, Baird RW, Basran C, Cabrera E, Calambokidis J, Cardoso J, Carroll EL, Cesario A, Cheney BJ, Corsi E, Currie J, Durban JW, Falcone EA, Fearnbach H, Flynn K, Franklin T, Franklin W, GallettiVernazzani B, Genov T, Hill M, Johnston DR, Keene EL, Mahaffy SD, McGuire TL, McPherson L, Meyer C, Michaud R, Miliou A, Orbach DN, Pearson HC, Rasmussen MH, Rayment WJ, Rinaldi C, Rinaldi R, Siciliano S, Stack S, Tintore B, Torres LG, Towers JR, Trotter C, TysonMoore R, Weir CR, Wellard R, Wells R, Yano KM, Zaeschmar JR, Bejder L

Publication type: Article

Publication status: Published

Journal: Methods in Ecology and Evolution

Year: 2023

Volume: 14

Issue: 10

Pages: 2611-2625

Online publication date: 13/07/2023

Acceptance date: 05/06/2023

Date deposited: 26/07/2023

ISSN (electronic): 2041-210X

Publisher: British Ecological Society

URL: https://doi.org/10.1111/2041-210X.14167

DOI: 10.1111/2041-210X.14167


Altmetrics

Altmetrics provided by Altmetric


Funding

Funder referenceFunder name
2201428
2232862
National Oceanic and Atmospheric Administration
National Science Foundation
NOAA Fisheries QUEST Fellowship
University of Hawaii Information Technology Services

Share