New AI tech helps pick the fittest fish
An Australian-first prototype tool developed by James Cook University researchers plans to give aquaculture farmers an edge in breeding the perfect catch.
The Mobile Fish Landmark Detection network (MFLD-net) uses a conveyer belt, industrial camera and an artificial intelligence algorithm to detect the ideal characteristics of barramundi in order to improve selective breeding practices.
Research lead Associate Professor Mostafa Rahimi Azghadi said the patented tool took digital images from fish passing under the camera which automatically predicted important characteristics of interest to farmers for grading and selective breeding.
That includes weight and length which would otherwise need to be manually collected.
“The idea is to gather as much data as possible on an industrial-scale on the characteristics of the fish from an image using computer vision and machine learning,” Associate Prof Azghadi said.
“The data captured may help aquaculture farmers with decision making – for example, which animals should be put together for selective breeding, or grading animals to sell to a particular market. This process can now be automated and scaled, saving a great deal of time and money.”
The algorithms, developed by PhD candidate Alzayat Saleh, firstly locates key data points on the body of a fish before using the relationships between landmarks to predict the weight or other characteristics of the animal.
“In order to train the algorithms, you need to begin by manually placing the landmarks on images from thousands of fish as a starting point,” Associate Prof Azghadi said.
“In our case we have done this for over 2500 fish images.”
In development for the past two years, the tool could have further applications for different types of seafood species, such as grouper, with trials planned with aquaculture industry partners by the end of this year.
JCU ARC Research Hub for Supercharging Tropical Aquaculture director Professor Dean Jerry said AI had “great potential” in improving the efficiency of many aspects of aquaculture production.
“We are actively working with aquaculture companies in order to collect data and validate AI tools,” he said.
Media enquiries: email@example.com