Automated Identification of Individual Great White Sharks from Unrestricted Fin Imagery

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.