SINTEF: Automated method for grading salmon fillets

Development Opportunity, Research Lead

Ekrem Misimi, a research scientist at SINTEF Fisheries and Aquaculture Research in Norway, has developed software combining machine vision with pattern recognition for the automatic grading of salmon.

Grading involves assessment of shape, colour and the presence of any surface injuries.  If the salmon was stressed at death it stiffens more rapidly. When stored on ice the fillets change colour and shape faster than fillets from an unstressed fish.

Stressed fillets cannot be processed until they have passed through rigor mortis after two or three days, and meanwhile the product is losing freshness. Moreover, there may be blood in the stomach cavity from when the salmon was bled, which can leave flecks on fresh and smoked fillets, a common cause of downgrading.

As yet there are no automated systems for making these assessments and fish are graded manually.

“The Norwegian fish-processing industry has been slow to introduce modern technology, and the production costs of a kilo of salmon are on average of 5 – 10 kroner higher than in competitor countries. Exports of processed salmon are low, so the industry has a lot to gain by adopting these new methods,” says Misimi.

The software holds a digitised version of the colour matching card that is used to assess if fillets fall within approved limits. This objective method agrees well with manual inspection, but is faster and does not require the fish to be handled.

“Machine vision and image analysis will enable us to sort fish into “production”, “ordinary” and “superior” classes, while revealing blood in the stomach cavity, with an accuracy of 90 percent. Automation can increase productivity and raise processing rates,” claims Misimi Ekrem.