- Anomaly detection
- Media data analysis
Inspection technology with the no-defects learning system
Enables rapid automation of inspection processes and increased inspection accuracy through AI image inspections using the “no-defects learning” approach.
- This AI image inspection technology using the “no-defects learning” approach is a solution for automating inspection processes in the front lines of manufacturing.
- With “no-defects learning” based on Toshiba’s original threshold optimization method, it is possible to prevent missed defects while at the same time reducing false positives. This approach conserves worker labor in inspection processes.
- Preparations for inspections (model construction) can be completed without gathering defects, which are rare in the front lines of volume production (uses acceptable products only).
- General image inspections of assembly items
Benchmarks, strengths, and track record
- Only acceptable product images are used as teaching data, enabling learning in a short time with just a few images.
- No specialized skills are needed to create an acceptable product model or adjust accuracy.
Inquiries to the Corporate Manufacturing Engineering Center of Toshiba Corporation
Please include the title “Toshiba AI Technology Catalog: Inspection technology with the no-defects learning system’” or the URL in the inquiry text.
Please note that because this technology is currently the subject of R&D activities, immediate responses to inquiries may not be possible.
- Automation Promotes Resilient Value Chains: Toshiba AI Technologies Foster Collaborations between Humans and Robots, Toshiba Clip, https://www.toshiba-clip.com/en/detail/p=443, Sep, 2020.
- Meister Apps™ AI visual inspection package