AI in Quality Control – Real Use Cases and Best Practices
summary
Optical inspection systems use infrared camera images plus meta tags and labeled training data to train a visual‑inspection AI; a cookie line PoC achieves about 98% PoC accuracy for cream fill and moves to rollout, and a glass‑bottle setup detects 12+ defect types earlier in the line. The solution runs on camera/on‑prem/cloud, integrates with actuators to sort scrap vs good parts, and succeeds only with uniform lighting, reliable images and operational integration.
AI-written summary · about
chapters (11)
- 0:00AI in quality control
- 1:29Optical quality control evolution
- 2:33Manual vs image processing challenges
- 3:58Visual inspection AI workflow
- 6:25Cookie filling detection use case
- 8:09Glass bottle defect detection
- 10:14AI project lifecycle POC to production
- 11:58Hardware and latency for AI models
- 13:44Success factors for AI QC
- 15:49Low-code AI tools for engineers
- 16:31Q&A
related talks
36mAI-Powered Real-Time Quality Control
27mComputer vision for automated quality inspection
59mAI in the Battle Against Fakes
43mAI for Testing – Panel Discussion
10mRealizing the Power of AI at the Edge
14mAI-Driven Precision Manufacturing
48mAI in the battle against fakes
06mAI in production: The droids you’re looking for