We describe a method that performs automated recognition of individual laetherback turtles within a large nesting population. With only minimal preprocessing required of the user, we prove able to produce unsupervised matching results. The matching is based on the Scale-Invariant Feature Transform by Lowe. A strict condition posed by biologists reads that matches should not be missed (no false negatives). A robust criterion is defined to meet this requirement. Results are reported for a considerable sample of leatherbacks.
Additional Metadata
Publisher Springer
Editor P. Perner
Series Lecture notes in artificial intelligence
Project Multimedia Understanding through Semantics, Computation and Learning
Citation
Pauwels, E.J.E.M, de Zeeuw, P.M, & Buonantony, D.M. (2008). Leatherbacks matching by automated image recognition. In P Perner (Ed.), Advances in Data Mining - Medical Applications, E-Commerce, Marketing and Theoretical Aspects (pp. 417–425). Springer.