This AI Can Grade Tuna Freshness | Tuna Scope - Popular Mechanics

jumi.indah.link

• Tuna Scope, a new app in Japan, uses artificial intelligence to grade the quality of cuts of tuna, mostly for sushi.
• The app lasers in on the tuna's tail, specifically, as an indicator of freshness.
• Fishmongers say that this is fine for chain restaurants, but high-end restaurants will always want the human touch.

---

Sushi is only as good as the fish wrapped inside its barrel of rice and seaweed. If the tuna, yellowtail, or salmon isn't fresh, it not only looks gross, but renders the whole roll underwhelming in flavor and texture.

To keep things from getting fishy, a Japanese company has developed a new mobile app that uses artificial intelligence to grade the freshness of cuts of tuna on sight. Aptly named Tuna Scope, the system uses thousands of cross-sectional images of tuna tails as training data to learn what good quality tuna looks like.

According to the Tuna Scope website, trained fishmongers use the tuna tail as a "road map" detailing the fish's flavor, texture, freshness, and overall excellence. Traditionally, master tuna merchants look at things like color and sheen, firmness, and the layering of fat to set fish prices. The silkier the meat looks, the better it probably tastes.

"The goal behind the development of this system was to pass down skills in the field of tuna evaluation, an area with a serious shortage of successors," Dentsu, the Tokyo-based digital marketing company that led development of the app, said in a press release.

Because this tacit knowledge is fading, the Dentsu team visited fishing ports, including one in Tsukiji, Tokyo, to interview tuna quality experts and tuna industry reps to figure out what to look for in a cut of tuna. From there, the company and its partners—including Sojitz Corporation, a major trading company that processes vast amounts of tuna each day—created an AI-based system to serve in the role of fishmonger.

A tuna quality expert evaluates the fish’s quality.

Dentsu

Cross sections of tuna tails that were used as AI training data.

Dentsu

To create training data for the deep learning algorithm, the companies began photographing cross-sections of tuna tail samples at one of Sojitz's client fisheries, ending up with over 4,000 images in total. From there, they built a four-step quality assessment system for the app.

This content is imported from YouTube. You may be able to find the same content in another format, or you may be able to find more information, at their web site.

In March 2019, the company began a relationship with a fishery in Yaizu, a city located in the central Shizuoka Prefecture, to test the Tuna Scope system. The Tuna Scope app had an 85 percent success rate in identifying tuna tails that met the four stage quality assessment typically conducted by tuna wholesalers with decades of experience. In other words, this app was pretty good at finding the cream of the crop.

Dentsu sys the AI systems isn't meant to replace human workers, but instead the image analysis algorithm could help to train the next generation of artisan tuna evaluators. But the overall goal, Dentsu says, is to really integrate the AI into the inspection process at fish factories, worldwide.

This content is created and maintained by a third party, and imported onto this page to help users provide their email addresses. You may be able to find more information about this and similar content at piano.io

The Link Lonk


July 10, 2020 at 02:41AM
https://ift.tt/3gE1k7i

This AI Can Grade Tuna Freshness | Tuna Scope - Popular Mechanics

https://ift.tt/2NKNaVQ
Tuna