Automated Identification of Individual Great White Sharks from Unrestricted Fin Imagery

Benjamin Hughes and Tilo Burghardt

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 an evaluation of the system components and report their performance and properties.

Session

Identification and Scene Annotation

Files

PDF iconExtended Abstract (PDF, 5M)
PDF iconPaper (PDF, 9M)
ZIP iconSupplemental Materials (ZIP, 12K)

DOI

10.5244/C.29.92
https://dx.doi.org/10.5244/C.29.92

Citation

Benjamin Hughes and Tilo Burghardt. Automated Identification of Individual Great White Sharks from Unrestricted Fin Imagery. In Xianghua Xie, Mark W. Jones, and Gary K. L. Tam, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 92.1-92.14. BMVA Press, September 2015.

Bibtex

@inproceedings{BMVC2015_92,
	title={Automated Identification of Individual Great White Sharks from Unrestricted Fin Imagery},
	author={Benjamin Hughes and Tilo Burghardt},
	year={2015},
	month={September},
	pages={92.1-92.14},
	articleno={92},
	numpages={14},
	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
	publisher={BMVA Press},
	editor={Xianghua Xie, Mark W. Jones, and Gary K. L. Tam},
	doi={10.5244/C.29.92},
	isbn={1-901725-53-7},
	url={https://dx.doi.org/10.5244/C.29.92}
}