Australian technology company, GoMicro, has created technology based on artificial intelligence which will help prevent spoiled tuna from reaching retail shelves in Sri Lanka.
Sourcing fresh tuna is a major problem for retailers in Sri Lanka with the National Aquatic Resources Research and Development Agency estimating that more than 30% of fish landed in the country is spoilt.
Assessing tuna is an art with tuna masters typically taking 20 years to learn how to grade tuna accurately. After six months in development with Keells supermarkets Go-Micro’s AI assessment technology can now match the judgement of tuna experts in differentiating fresh tuna from that which is likely to spoil before it reaches the store.
“Keells has now tested GoMicro AI to assess the quality of Yellowfin Tuna,” said Mifrah Ismail, head of fresh food and vice president at the John Keells Group. “GoMicro AI can accurately differentiate fresh tuna from tuna that is spoilt,” he added.
GoMicro’s AI technology uses machine learning to compare images with a database. “We are able to achieve high accuracies using a much smaller number of training images than our competition, due to our patented phone-based imaging technology,“ commented Jarrad Law, chief technology officer and co-founder at GoMicro.
The technology also managed to accurately determine a fresh tuna just by looking at its eyes – as consumers do – in four out of five cases. GoMicro is now working with a company based at the Sydney Fish Market to grade oysters as these are also typically graded by eye.