Embedded Files
Photographic-identification is an important tool used by many researchers to study cetaceans over a wide variety of temporal and spatial scales. Recently, several automated algorithms have been developed to identify cetacean dorsal fins and improve the efficiency of the matching process. However, there has been little discussion among users regarding the efficacy or accuracy of these systems. We aim to bring together photo-ID researchers and database and algorithm developers to identify strengths and weaknesses of automated fin-matching systems; evaluate their success in matching dorsal fins; and assess their application in photo-ID workflows. Our goal is to derive a set of best practices for using fin recognition technology, and to assess whether a single ‘standard’ system can be developed for automated dorsal fin photo-ID.
If you are a researcher (or lab group) using photo-ID techniques for matching dorsal fins, please consider helping us achieve these goals by exploring this site and:
- Completing our survey on photo-ID methods for matching dorsal fins (approximately 10 minutes)
- Testing your photo-ID matching system with our test data to allow a direct comparison of performance among systems ('systems' include manual matching, user-defined attribute-based matching, and computer vision matching systems) (approximately 2 hours)
Results from these efforts will be discussed at the “Rise of the machines - Application of automated systems for matching dolphin dorsal fins: current status and future directions” workshop to be held on Sunday, December 8, 2019, at the World Marine Mammal Conference in Barcelona, Spain. In addition, the results of these tests and discussions will be prepared and distributed to the photo-ID community on this website and via a manuscript that will be drafted for peer-review in Marine Mammal Science (or other appropriate scientific journal).
Thank you in advance for your help and participation,
Reny Tyson Moore
Chicago Zoological Society’s Sarasota Dolphin Research Program, Sarasota, FL USA
rtysonmoore@mote.org
Kim Urian
Duke University Marine Laboratory, Beaufort, NC USA
kim.urian@gmail.com
Page updated
Report abuse