South KoreaHealthcare and life sciences2026 – ongoingHandok
AI inspection of Ketotop packaging
Handok reported fewer false rejections after training AI cameras on Ketotop packaging
Problem
Packaging inspection needed to distinguish defective products from acceptable ones. Early AI inspections incorrectly rejected some normal products.
Approach
Handok installed AI machine-vision cameras on parts of its operating packaging lines in Eumseong. The cameras classified products from images using learned examples. Staff repeatedly trained the system with normal and defective product data to improve inspection accuracy.
Results
No published figures
Takeaway
The production manager attributed improved packaging yield to fewer false rejections. Handok did not disclose the size of the yield improvement.
Categories
- Industry
- Healthcare and life sciences
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Computer vision
- Adoption
- Vendor solution
- Goal
- Quality and risk
- Evidence
- Company's own claim
Sources
Source summaries
A factory visit described AI cameras inspecting products on Ketotop packaging lines. Handok's production manager said repeated training reduced false rejections and improved yield; broader autonomous manufacturing functions remained under development or testing.
Full details are in the original sources.