Asia Business Channel

Japanese sushi chain uses AI to grade the quality of fish


“The Tuna Scope application assesses characteristics like fat content and color”

Beginning in 1967, Dentsu, Japan and the world’s largest advertising agency had its headquarters in Tokyo’s Tsukiji district, which was also home to the world famous Tsukiji fish market, so its no coincidence that Dentsu was asked by a Japanese chain of sushi restaurants to help it develop an Artificial Intelligence (AI) app to assess the quality of tuna and price for tuna that will be prepared as sushi.

Normally it takes years of experience and training for humans to be able to determine the quality of tuna used in Japanese sushi, and with fewer people entering the sushi restaurant business, an AI app is considered necessary for the industry to survive.

The Dentsu app, named Tuna Scope, uses machine learning algorithms trained on thousands of images of the cross-sections of tuna tails, a part of the tuna that can reveal crucial details that relate to the quality of the fish.


The “Tuna Scope” app has been developed using thousands of images of tuna tails / Photo courtesy of Dentsu

From a single picture of the tuna, the app grades the tuna on a five-point scale based upon visual characteristics of each fish, such as the sheen of the flesh and the layering of fat. For a human who is an experienced fish grader, these attributes speak volumes about the sort of life the fish led, what it ate, and how active it was and what the flavor of the fish will be.

Dentsu said that the AI powering Tuna Scope has captured the “unexplainable nuances of the tuna examination craft,” and that in tests that compared the apps grading of tuna with human buyers, the app issued the same grade more than four times out of five.


Dentsu’s app uses machine-Learning algorithms to assess the tuna from a single picture / Photo courtesy of Dentsu

A sushi chef who has graded sushi says that the highest-quality tuna has an intense bright red color and a certain degree of translucency as if the flesh is almost glowing. “It looks bouncy, or soft, maybe, to your eye. Good quality tuna is silkier and shiny, and that it seems possible to use AI to make basic assessments of the quality.”

According to a report by Japan’s Asahi Shimbun, Tuna Scope is being used by the restaurant chain Kura Sushi to grade fish for its restaurants. Kura Sushi reportedly purchases 70% of its fish for sushi overseas and the app allows local agents to make on-the-spot assessments of fish that the restaurant wants to buy.


Chefs and fishmongers judge the quality of tuna based on the sheen and color of the flesh / Photo courtesy of Dentsu

But while this sort of automation might work for a large chain like Kura Sushi, some people say that it won’t meet the demands of high-end chefs and traditional sushi aficionados.

A chef at a traditional sushi restaurant in Tokyo said that using an app would break that chain of trust with its customers, who expect a traditional sushi experience to include chefs buying fish only after they have personally viewed the fish they use before they are served to customers.




Read 107