South KoreaFood and restaurants2024 – ongoingKorea Institute for Animal Products Quality Evaluation
AI-assisted egg appearance and crack grading
Korea's animal-products grading institute reported 11-minute AI egg checks versus 30 minutes manually
Problem
Egg grading required inspectors to assess shell appearance and detect cracks, including fine defects. Manual checks took time and could miss small cracks.
Approach
The institute developed AI grading equipment in 2024 and began field testing in 2025. At YJ Food, inspectors operated equipment that rotated eggs for surface photography and used transmitted-light images to detect cracks. Destructive freshness testing remained manual, and final grades combined the different assessments.
Results
Takeaway
AI covered visual inspection within a wider grading process. Freshness tests still required a separate manual procedure.
Categories
- Industry
- Food and restaurants
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Computer vision
- Adoption
- Built in-house
- Evidence
- Company's own claim
Sources
Source summaries
A reporter observed inspectors operating the equipment at YJ Food. An institute official reported 11-minute checks for 10 trays compared with 30 minutes manually; the report explained which grading tasks remained manual.
Full details are in the original sources.