Background

Tuna―one of the ocean’s greatest treasures. The Tokyo market is a global center for marine products, where tuna examiners judge the quality of fish with their eyes. However, due to a shrinking fisheries industry and Tokyo’s rapidly aging population, the number of craftsmen has fallen to less than half of the industry’s golden age. In the near future, it’s feared that there will be no successors to carry on the occupation. Sojitz is a trading company that handles tuna from fishing grounds all over the world, and is committed to managing the quality of its own tuna by unifying standards by dispatching craftsmen around the world. To keep delivering a high standard of tuna in a future when tuna examiners may not be around, the company took the challenge of creating something that could carry on the legacy of this trade by developing a new system using AI.

Describe the creative idea

We focused on cross sections of the tuna’s tail, which hold all the vital information about the tuna’s flavor, freshness and so forth. Craftsmen who worked at markets had long used this technique to examine tuna, but it is said it takes at least ten years to learn to develop the acumen to perform this feat by eye. Utilizing an environment that saw a number of tuna thousands of times greater than a single examiner might see, we photographed a massive number of tuna tail cross sections, and through deep learning, we taught AI to interpret this data, and master the craft’s unexplainable nuances in a single month—an impossibly short time for humans. This project resulted in the birth of a system which could analyze and master the hidden nuances of the examination process, which practitioners themselves admitted were nearly impossible to explain.

Describe the strategy

Up until now, tuna examination has been the domain of a group of individual artisans, each with their own personal nuanced methods, and as such, has been difficult to reduce into a generalized technique. Since the number of tuna each examiner could practice on is limited, it also takes a great deal of time to train. We created a system by which we introduced an AI on a mobile platform into the large network operated by the client, Sojitz, and allowed it to learn simultaneously from a huge amount of visual data from fish markets all over the world. This enabled the creation of a unified standard of tuna examination by gathering many artisans’ experiences on a single application.

Describe the execution

The AI system developed for TUNA SCOPE was turned into a smartphone app and introduced to the quality inspection process in fish factories. As a result, it was able to achieve 85% accuracy compared to real tuna examiners with 35 years of experience in dividing the fish into 4-5 grades. The tuna ranked highest by the AI during this test was branded as AI Tuna and served at a sushi restaraunt in Tokyo in order to test market viability. 12/8/2017 - Prototype development begins 3/1/2018 - Development and successful test 3/5/2019 - TUNA SCOPE introduced to factory 3/27/2019 - AI TUNA is served in Tokyo and introduced as a brand 4/2019 - Brainstorming for use in other industries (agriculture, medicine, etc.) 4/25/2019 - Website launches 5/29/2019- Press release distribution

List the results

Over two years from its conception, the developed AI system, TUNA SCOPE was implemented as a smartphone application, and introduced to the quality judgment flow in fishery factories. It achieved about an 85% consensus rate with 35 year veteran practitioners of the craft in appraisal of a 4-5 grade quality assessment. Of the several hundred tuna examined, the tuna ranked as the highest level of reliability and quality by the AI were branded and sold as “AI Tuna” at sushi restaurants in Tokyo. We achieved about 90% customer satisfaction. Going forward, we plan on deploying the system to our network. By learning data from our fishing grounds simultaneously, we will establish a uniform standard for appraisal, and aim to create a world where people everywhere can eat delicious tuna. The algorithm developed for this project has potential for use across a wide range of industries.