University of Tasmania scientists have built an artificial intelligence system that identifies individual southern rock lobsters from a simple photo, removing the need for physical tags in the live export industry.
Researchers at the Institute for Marine and Antarctic Studies developed the technology to trace lobsters through processing and export using images captured on a mobile device.
“We’ve created a non-invasive traceability system for live southern rock lobsters that is incredibly robust, scoring 100% accuracy on the test set and real-world data, with processing times of less than a second,” said Dean Giosio, an aquaculture engineer at IMAS.
The system works because each lobster carries unique patterns on its shell, acting like a fingerprint.
“Lobsters have unique patterns and the AI model recognises individual lobsters based on those features. It’s essentially a fingerprint which allows us to digitally tag lobsters,” said Tara Kelly, a junior researcher in aquatic animal physiology at IMAS.
The project, led by Professor Quinn Fitzgibbon and completed with Fiordland Lobster Company and the South Australian Lobster Company, involved capturing images of more than a thousand lobsters to train the system.
Fitzgibbon said traceability is key for building trust across the sector.
“Being able to verify where a lobster has come from and how it has been handled and transported creates reassurance for provenance claims and improves confidence in southern rock lobster as a premium product for Australia and New Zealand,” he said.
The model even works on images taken three years apart, despite growth and shell changes.
Researchers are now working to have the system automatically log details such as colour, sex and damage, with Giosio saying this will “lead to automated grading to improve factory efficiency, reduce costs and most importantly reduce stress to the lobsters.”
Beyond export, the technology could help track wild populations when undersized or egg-carrying lobsters are photographed and returned to the water.
The system will be deployed via a website and phone app, with potential to support recreational fishers and citizen science.
The project is funded by the iMOVE CRC and supported by the Australian Government’s Cooperative Research Centres program.
