• Login
  • Register
  • Search

A deep learning algorithm and software for photo identification of the Indo-Pacific humpback dolphin (Sousa chinensis)

Fuxing Wu, Neng Chen, Weilin Gao, Mengda Yu, Siying Huang, Mingding Zhong, Zhulin An, Xianyan Wang


Deep neural networks have been increasingly used to identify individual animals in ecological studies by learning and distinguishing their naturally occurring marks or features. Traditional individual animal recognition requires prior knowledge and experience, which can be time-consuming and inefficient. In this paper, a distinctive deep learning framework that automatically reidentifies individual Indo-Pacific humpback dolphins (Sousa chinensis) from photos was proposed. For most dolphin species with a dorsal fin, this feature is reliably used to identify and distinguish individuals in studies that require distinction between members of a group or population. Feature cutting and background removing strategies were added to allow a focus on local information. Knowledge distillation was also applied to improve the robustness of the framework. Additionally, an automatic dolphin recognition software suite for cetologists that may reduce the amount of effort and time required to manually confirm individual dolphin ID from photographs had been developed. In the end, the effectiveness of applying this deep neural network approach for individual Indo-Pacific humpback dolphin recognition had been demonstrated.


Indo-Pacific humpback dolphin; computer vision; re-identification; knowledge distillation; recognition software; Sousa chinensis

Full Text:


Included Database


Kreho A, Kehtarnavaz N, Araabi B, et al. Assisting manual dolphin identification by computer extraction of dorsal ratio. Annals of Biomedical Engineering 1999; 27: 830–838. doi: 10.1114/1.235

Wu F, Wang X, Ding X, et al. Distribution pattern of Indo-Pacific humpback dolphins (Sousa chinensis) along coastal waters of Fujian Province, China. Aquatic Mammals 2014; 40(4): 341–349. doi: 10.1578/AM.40.4.2014.341

Wang X, Wu F, Turvey ST, et al. Social organization and distribution patterns inform conservation management of a threatened Indo-Pacific humpback dolphin population. Journal of Mammalogy 2015; 96(5): 964–971. doi: 10.1093/jmammal/gyv097

Wang X, Wu F, Chang W, et al. Two separated populations of the Indo-Pacific humpback dolphin (Sousa chinensis) on opposite sides of the Taiwan Strait: Evidence from a larger-scale photo-identification comparison. Marine Mammal Science 2016; 32(1): 390–399. doi: 10.1111/mms.12257

Nichols, JD. Capture-recapture models: Using marked animals to study population dynamics. BioScience 1992; 42(2): 94–102. doi: 10.2307/2937171

Würsig B, Jefferson TA. Methods of photo-identification for small cetaceans. Reports of the International Whaling Commission 1990; 12: 43–52.

Hammond PS, Mizroch SA, Donovan GP. Individual recognition of cetaceans: Use of photo-identification and other techniques to estimate population parameters. International Whaling Commission; 1990.

Auger-Méthé M, Whitehead H. The use of natural markings in studies of long-finned pilot whales (Globicephala Melas). Marine Mammal Science 2006; 23(1): 77–93. doi: 10.1111/j.1748-7692.2006.00090.x

Ye M, Shen J, Lin G, et al. Deep learning for person re-identification: A survey and outlook. IEEE Transactions on Pattern Analysis and Machine Intelligence 2020; 44(6): 2872–2893. doi: 10.1109/TPAMI.2021.3054775

Manlik O, McDonald JA, Mann J, et al. The relative importance of reproduction and survival for the conservation of two dolphin populations. Ecology and Evolution 2016; 6(11): 3496–3512. doi: 10.1002/ece3.2130

Jefferson TA, Karczmarski L. Sousa chinensis. Mammalian Species 2001; (655): 1–9. doi: 10.2307/0.655.1

Liu L, Ouyang W, Wang X, et al. Deep learning for generic object detection: A survey. International Journal of Computer Vision 2020; 128(2): 261–318. doi: 10.1007/s11263-019-01247-4

Hinton GE, Vinyals O, Dean J. Distilling the knowledge in a neural network. ArXiv E-print 2015; arXiv:1503.02531. doi: 10.48550/arXiv.1503.02531

Cheng D, Gong Y, Zhou S, et al. Person re-identification by multi-channel parts-based CNN with improved triplet loss function. In: Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 27–30 June 2016; Las Vagas, NV, USA. pp. 1335–1344. doi: 10.1109/CVPR.2016.149

Zheng L, Zhang H, Sun S, et al. Person re-identification in the wild. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 21–26 July 2017; Honolulu, HI, USA. pp. 3346–3355. doi: 10.1109/CVPR.2017.357

Luo H, Jiang W, Gu Y, et al. A strong baseline and batch normalization neck for deep person re-identification. IEEE Transactions on Multimedia 2020; 22(10): 2597–2609. doi: 10.1109/TMM.2019.2958756

Wang G, Yuan Y, Chen X. Learning discriminative features with multiple granularities for person re-identification. In: Proceedings of the 26th ACM International Conference on Multimedia; 22–26 October 2018; Seoul, Republic of Korea. pp. 274–282. doi: 10.1145/3240508.3240552

Sun Y, Zheng L, Yang Y, et al. Beyond part models: Person retrieval with refined part pooling (and A Strong Convolutional Baseline). In: Ferrari V, Hebert M, Sminchisescu C, Weiss Y (editors). Computer Vision—ECCV 2018. Lecture Notes in Computer Science, Proceedings of 15th European Conference on Computer Vision (ECCV); 8–14 September 2018; Munich, Germany. pp. 501–518. doi: 10.1007/978-3-030-01225-0_30

Zhao H, Tian M, Sun S, et al. Spindle net: Person re-identification with human body region guided feature decomposition and fusion. In: 2017 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 21–26 July 2017; Honolulu, HI, USA. pp. 907–915. doi: 10.1109/CVPR.2017.103

Liu C, Zhang R, Guo L. Part-pose guided amur tiger re-identification. In: Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW); 27–28 October 2019; Seoul, Korea (South). pp. 315–322. doi: 10.1109/ICCVW.2019.00042

Krschens M, Barz B, Denzler J. Towards automatic identification of elephants in the wild. ArXiv E-print 2018; arXiv:1812.04418. doi: 10.48550/arXiv.1812.04418

Bouma S, Pawley MDM, Hupman K, Gilman A. Individual common dolphin identification via metric embedding learning. In: Proceedings of the 2018 International Conference on Image and Vision Computing New Zealand (IVCNZ); 19–21 November 2018; Auckland, New Zealand. pp. 1–6. doi: 10.1109/IVCNZ.2018.8634778

Weideman HJ, Jablons ZM, Holmberg J, et al. Integral curvature representation and matching algorithms for identification of dolphins and whales. In: Proceedings of the 2017 IEEE International Conference on Computer Vision Workshops (ICCVW); 22–29 October 2017; Venice, Italy. pp. 2831–2839. doi: 10.1109/ICCVW.2017.334

Hughes B, Burghardt T. Automated visual fin identification of individual great white sharks. International Journal of Computer Vision 2017; 122(3): 542–557. doi: 10.1007/s11263-016-0961-y

Feng J. Photo Identification of Chinese White Dolphin Based on Deep Learning [Master’s thesis]. Shantou University; 2020.

Deng J, Guo J, Zhou Y, et al. RetinaFace: Single-stage dense face localisation in the wild. ArXiv E-print 2019; arXiv:1905.00641. doi: 10.48550/arXiv.1905.00641

Redmon J, Farhadi A. YOLOv3: An incremental improvement. ArXiv E-print 2018; arXiv:1804.02767. doi: 10.48550/arXiv.1804.02767

Hermans A, Beyer L, Leibe B. In defense of the triplet loss for Person re-identification. ArXiv E-print 2017; arXiv:1703.07737. doi: 10.48550/arXiv.1703.07737

Russakovsky O, Deng J, Su H. et al. Imagenet large scale visual recognition challenge. International Journal of Computer Vision 2015; 115: 211–252. doi: 10.1007/s11263-015-0816-y

He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 27–30 June 2016; Las Vegas, NV, USA. pp. 770–778. doi: 0.1109/CVPR.2016.90

DOI: http://dx.doi.org/10.18686/me.v12i1.9205