Automated Identification of Individual Great White Sharks from Unrestricted Fin Imagery

Benjamin J Hughes, Tilo Burghardt

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

628 Downloads (Pure)

Abstract

The objective of this paper is automatically to identify individual great white sharks in a database of thousands of unconstrained fin images. The approach put forward appreciates shark fins in natural imagery as smooth, flexible and partially occluded objects with an individuality encoding trailing edge. In order to recover animal identities therefrom. We first introduce an open contour stroke model which extends multi-scale region segmentation to achieve robust fin detection. Secondly, we show that combinatorial spectral fingerprinting can successfully encode individuality in fin boundaries. We combine both approaches in a fine-grained multi-instance recognition framework. We provide a detailed evaluation of the system components and report its performance and properties.
Original languageEnglish
Title of host publicationProceedings of the 26th British Machine Vision Conference (BMVC)
PublisherBritish Machine Vision Association
Pages92.1-92.14
Number of pages14
ISBN (Print)1901725537
DOIs
Publication statusPublished - Sep 2015

Keywords

  • animal biometrics
  • computer vision

Fingerprint Dive into the research topics of 'Automated Identification of Individual Great White Sharks from Unrestricted Fin Imagery'. Together they form a unique fingerprint.

  • Projects

    RCUK FELLOW

    Ulcigrai, C.

    1/08/071/08/12

    Project: Research

    Cite this

    Hughes, B. J., & Burghardt, T. (2015). Automated Identification of Individual Great White Sharks from Unrestricted Fin Imagery. In Proceedings of the 26th British Machine Vision Conference (BMVC) (pp. 92.1-92.14). British Machine Vision Association. https://doi.org/10.5244/C.29.92