The dusky grouper (Epinephelus marginatus) is one of the most iconic fish of the Mediterranean Sea. It is also one of the most endangered, the species having already come close to disappearing from the coasts of the northern Mediterranean. In 1993, the first protection moratorium allowed the populations to strengthen, particularly in marine protected areas.
The dusky grouper is now protected by a moratorium valid until 2023, which prohibits all forms of fishing except with nets. Nevertheless, the species remains classified as "Endangered" in the International Union for Conservation of Nature (IUCN) Red List for the Mediterranean area. It is therefore necessary to maintain conservation efforts for this species and particularly the monitoring of individuals.
In order to provide scientists with robust and reliable data to be used for the evaluation of the grouper population, a tool for individual recognition based on Deep Learning or epipolar geometry* would be an ideal tool for extracting key data such as: abundance, site fidelity, movements between dive sites etc... As individual recognition of groupers is possible thanks to the unique patterns of the spots located on the head, we would like to build a database of annotated photographs of Grouper in order to train the recognition algorithms.
In order to collect as many photos as possible, a citizen scientific approach will be used. Thus, a collaborative platform "NaturDive Watch" will be developed to offer to any diver the possibility to upload his photos with the required associated information.
To brainstorm together and discover how to create an annotated photo database of grouper to identify individuals by facial recognition, join us on Tuesday 6 July at 5 pm on https://meet.jit.si/HACK4NATURE for the launch of the challenge!