Cheeseman T. auteur aut IRD Southerland K. auteur aut IRD Park J. auteur aut IRD Olio M. auteur aut IRD Flynn K. auteur aut IRD Calambokidis J. auteur aut IRD Jones L. auteur aut IRD Garrigue Claire auteur aut IRD Jordan A. F. auteur aut IRD Howard A. auteur aut IRD Reade W. auteur aut IRD Neilson J. auteur aut IRD Gabriele C. auteur aut IRD Clapham P. auteur aut IRD text journalArticle eng text/pdf born digital access We describe the development and application of a new convolutional neural network-based photo-identification algorithm for individual humpback whales (Megaptera novaeangliae). The method uses a Densely Connected Convolutional Network (DenseNet) to extract special keypoints of an image of the ventral surface of the fluke and then a separate DenseNet trained to look for features within these keypoints. The extracted features are then compared against those of the reference set of previously known humpback whales for similarity. This offers the potential to successfully automate recognition of individuals in large photographic datasets such as in ocean basin-wide marine mammal studies. The algorithm requires minimal image pre-processing and is capable of accurate, rapid matching of fair to high-quality humpback fluke photographs. In real world testing compared to manual image matching, the algorithm reduces image management time by at least 98% and reduces error rates of missing potential matches from approximately 6-9% to 1-3%. The success of this new system permits automated comparisons to be made for the first time across photo-identification datasets with tens to hundreds of thousands of individually identified encounters, with profound implications for long-term and large population studies of the species. specialized Automated image recognition Computer vision Deep convolutional neural networks Kaggle competition Machine learning Mark recapture Megaptera novaeangliae Photo-ID 034 122 102 3 [15 p.] 2022 1616-5047 https://www.documentation.ird.fr/hor/fdi:010083828 10.1007/s42991-021-00180-9 1616-5047 [F B010083828] https://www.documentation.ird.fr/hor/fdi:010083828 https://www.documentation.ird.fr/intranet/publi/2022-01/010083828.pdf Accès réservé (Intranet de l'IRD) IRD - Base Horizon / Pleins textes 2022-01-12 2023-04-05 fdi:010083828 fre