Advertisement

RETRACTED CHAPTER: Towards End-to-End DNN-Based Identification of Individual Manta Rays from Sparse Imagery

  • Tuana CelikEmail author
  • Benjamin Hughes
  • Tilo Burghardt
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11401)

Abstract

This paper presents an end-to-end deep learning approach for the fine-grained identification of individual manta rays (Manta alfredi) based on characteristic ventral coat patterns where training is restricted to sparse photographic sets of <10 ventral images per individual. The dataset is captured by divers in underwater habitats. Its content is challenging due to non-linear deformations (of the rays), perspective pattern distortions, partial occlusions, as well as lighting and noise-related acquisition issues. We show how a combination of data augmentation, encounter fusion, and transfer learning techniques can address the sparsity and noise challenges at hand so that deep learning pipelines can operate effectively in this uncompromising data environment. We demonstrate that using the proposed approach with an adapted InceptionV3 deep neural network (DNN) architecture significantly outperforms tested baselines including the Manta Matcher approach, the so-far best performing traditional, widely used method published for the application at hand.

References

  1. 1.
    Kühl, H., Burghardt, T.: Animal biometrics: quantifying and detecting phenotypic appearance. Trends Ecol. Evol. 28, 432–441 (2013)CrossRefGoogle Scholar
  2. 2.
    Town, C., Marshall, A., Sethasathien, N.: Manta matcher: automated photographic identification of manta rays using keypoint features. Ecol. Evol. 3, 1902–1914 (2013)CrossRefGoogle Scholar
  3. 3.
    Loos, A., Ernst, A.: An automated chimpanzee identification system using face detection and recognition. EURASIP Image Video Process. 2013(1), 49 (2013)CrossRefGoogle Scholar
  4. 4.
    Hughes, B., Burghardt, T.: Automated visual fin identification of individual great white sharks. IJCV 122(3), 542–557 (2017)CrossRefGoogle Scholar
  5. 5.
    Lowe, D.G.: Object recognition from local scale-invariant features. In: IEEE International Conference on Computer Vision, vol. 2, pp. 1150–1157 (1999)Google Scholar
  6. 6.
    Bay, H., Tuytelaars, T., Van Gool, L.: SURF: Speeded Up Robust Features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 404–417. Springer, Heidelberg (2006).  https://doi.org/10.1007/11744023_32CrossRefGoogle Scholar
  7. 7.
    Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of IEEE CVPR, pp. 779–788 (2016)Google Scholar
  8. 8.
    Branson, S., Van Horn, G., Belongie, S., Perona, P.: Bird species categorization using pose normalized deep convolutional nets. arXiv:1406.2952 (2014)
  9. 9.
    Kumar, N., et al.: Leafsnap: a computer vision system for automatic plant species identification. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, pp. 502–516. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-33709-3_36CrossRefGoogle Scholar
  10. 10.
    Brust, C.-A., et al.: Towards automated visual monitoring of individual gorillas in the wild. In: Proceedings of IEEE CVPR, pp. 2820–2830 (2017)Google Scholar
  11. 11.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 25, pp. 1097–1105. Curran Associates Inc. (2012)Google Scholar
  12. 12.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556, pp. 1929–1958 (2014)
  13. 13.
    Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of IEEE CVPR, pp. 2818–2826 (2016)Google Scholar
  14. 14.
    Freytag, A., Rodner, E., Darrell, T., Denzler, J.: Exemplar-specific patch features for fine-grained recognition. In: Jiang, X., Hornegger, J., Koch, R. (eds.) Pattern Recognition, pp. 144–156. Springer, Cham (2014)Google Scholar
  15. 15.
    Freytag, A., Rodner, E., Simon, M., Loos, A., Kühl, H.S., Denzler, J.: Chimpanzee faces in the wild: log-euclidean CNNs for predicting identities and attributes of primates. In: Rosenhahn, B., Andres, B. (eds.) GCPR 2016. LNCS, vol. 9796, pp. 51–63. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-45886-1_5CrossRefGoogle Scholar
  16. 16.
    Andrew, W., Greatwood, C., Burghardt, T.: Visual localisation and individual identification of Holstein Friesian cattle via deep learning. In: IEEE International Conference on Computer Vision Workshop, pp. 2850–2859 (2017)Google Scholar
  17. 17.
    Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: Proceedings of IEEE CVPR, pp. 248–255, June 2009Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.University of BristolBristolUK
  2. 2.Save Our Seas FoundationGenevaSwitzerland
  3. 3.The Manta TrustDorchesterUK

Personalised recommendations