Wild Cetacea Identification using Image Metadata


  • Débora Pollicelli CESIMAR-CONICET, Centro para el Estudio de Sistemas Marinos, Consejo Nacional de Investigaciones Cient ́ıficas y T ́ecnicas, CCT CENPAT, Bv. Almirante Brown 2915, 9120, Puerto Madryn, Chubut, Argentina
  • Mariano Coscarella CESIMAR-CONICET, Centro para el Estudio de Sistemas Marinos, Consejo Nacional de Investigaciones Cient ́ıficas y T ́ecnicas, CCT CENPAT, Bv. Almirante Brown 2915, 9120, Puerto Madryn, Chubut, Argentina
  • Claudio Delrieux Laboratorio de Ciencias de las Imágenes, Departamento de Ingenier ́ıa El ́ectrica y Computadoras, Universidad Nacional del Sur y CONICET, 8000 Bahía Blanca, Argentina –


machine learning, photo-identification, cetaceans, Commerson’s dolphins


Identification of individuals in marine species, especially in Cetacea, is a critical task in several biological and ecological endeavours. Most of the times this is performed through human-assisted matching within a set of pictures taken in different campaigns during several years and spread around wide geographical regions. This requires that the scientists perform laborious tasks in searching through archives of images, demanding a significant cognitive burden which may be prone to intra- and interobserver operational errors. On the other hand, additional available information, in particular the metadata associated to every image, is not fully taken advantage of. The present work presents the result of applying machine learning techniques over the metadata of archives of images as an aid in the process of manual identification. The method was tested on a database containing several pictures of 223 different Commerson’s dolphins (Cephalorhynchus commersoni) taken over a span of seven years. A supervised classifier trained with identifications made by the researchers was able to identify correctly above 90% of the individuals on the test set using only the metadata present in the image files. This reduces significantly the number of images to be manually compared, and therefore the time and errors associated with the assisted identification process.


Download data is not yet available.


[1] K. H. Pollock, J. D. Nichols, C. Brownie, and J. E. Hines, Statistical inference for capture-recapture experiments, vol. 107 of Wildlife Monographs. Blacksburg: The Wildlife Society Inc., 1990.
[2] H. Whitehead, “Mark-recapture estimates with emigration and re-immigration,” Biometrics, vol. 46, pp. 473–479, 1990.
[3] R. M. Cormack, Models for capture-recapture, pp. 217–255. Maryland: International Cooperative Publishing House, 1979.
[4] M.Bigg, “An assessment of killer whale (orcinus orca) stocks of vancouver island, british columbia,” report, International Whaling Commission, 1982.
[5] P. S. Hammond, S. A. Mizroch, and G. P.Donovan, Individual recognition of cetaceans: Use of photo-identification and other techniques to estimate population parameters, vol. 12 of International Whaling Commission Special Issue Series. Cambridge: International Whaling Commission, 1990.
[6] B. WÃijrsig and M. WÃijrsig, “The photographic determination of group size, composition and stability of coastal porpoises (tursiops truncatus),” Science, vol. 198, pp. 755–756, 1977.
[7] E. College, “Darwin.” http://darwin.ekerd.edu/.
[8] T. A. University, “Fin scan.”
[9] J. Stewman, K. Debure, S. Hale, and A. Russell, “Iterative 3-d pose correction and content-based image retrieval for dorsal fin recognition,” in International Conference Image Analysis and Recognition, pp. 648–660, Springer, 2006.
[10] M. A. Coscarella, S. Gowans, S. N. Pedraza, and E. A. Crespo, “Influence of body size and ranging patterns on delphinid sociality: Associations among commerson’s dolphins,” Journal of Mammalogy, vol. 92, no. 3, pp. 544–551, 2011.
[11] M. A. Coscarella, Ecologı́a, comportamiento y evaluación del impacto de embarcaciones sobre manadas de tonina overa Cephalorhynchus commersonii en Bahı́a Engaño, Chubut. Ph.d., 2005.
[12] M. J. R. Q. C. Ferri Ramı́rez Alhambra, J. H. Orallo, Introducción a la minerı́a de datos. Pearson, 2004.
[13] I. H. Witten, E. Frank, and M. A. Hall, Data Mining: Practical Machine Learning Tools and Techniques. San Francisco, CA, USA: Morgan Kaufmann Publishers Inc., 3rd ed., 2011.
[14] M. Hall, E. Frank, G. Holmes, B. Pfahringer, and I. H. Witten, “The WEKA data mining software: An update,” SIGKDD Explorations, vol. 11, no. 1, pp. 10–18, 2009.
[15] M. L. G. at the University of Waikato, “Weka 3: Data mining software in java.” http://www.cs.waikato.ac.nz/ml/weka/.
[16] R. R. Bouckaert, E. Frank, M. Hall, R. Kirkby, P. Reutemann, A. Seewald, and D. Scuse, WEKA Manual for Version 3-6-12, 2014.
[17] O. L. González, J. F. M. Trinidad, and M. G. Borroto, “Clasificadores supervisados basados en patrones emergentes para bases de datos con clases desbalanceadas,” Tech. Rep. CCC-14-004.14, Coordinación de Ciencias Computacionales. INAOE, Luis Enrique Erro 1. Sta. Ma. Tonantzintla, 72840, Puebla, México., 2014.




How to Cite

Pollicelli, D., Coscarella, M., & Delrieux, C. (2017). Wild Cetacea Identification using Image Metadata. Journal of Computer Science and Technology, 17(01), p. 79–84. Retrieved from https://journal.info.unlp.edu.ar/JCST/article/view/447



Invited Articles