South KoreaFood and restaurants2024 – ongoingDongwon Industries
AI tuna-quality grading
Dongwon Industries applied a tuna-grading AI trained on more than 10,000 tail-section images
Problem
Staff graded frozen tuna by visually inspecting cut tail sections.
Approach
Dongwon developed a deep-learning model using tail-section images and grading criteria. Its CEO said the model was being applied to grading.
Results
No published figures
Takeaway
The company reported more standardized grading without disclosing accuracy.
Categories
- Size
- Large enterprise
- Industry
- Food and restaurants
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Computer vision
- Adoption
- Built in-house
- Goal
- Quality and risk
- Evidence
- Company's own claim
Sources
Source summaries
[1]The Chosun Ilbo27 Feb 2024
Dongwon's CEO described a tuna-grading model trained on more than 10,000 tail-section images. He attributed improved work efficiency and more standardized grading to the model.
Full details are in the original sources.
Added 1 Nov 2026 · Updated 1 Nov 2026