Eye-tracking AI platform for automated visual quality
This technology combines eye-tracking with an AI language model to automate quality inspection decisions in manufacturing. A camera watches where a human inspector's eyes move and pause on an image of a product, treating that sequence of visual attention as a kind of 'sentence.' That sentence is then fed into an AI model that interprets the inspector's visual reasoning and outputs a pass/fail classification. The result is a system that can learn how expert humans inspect items and replicate or assist that judgment programmatically.
What you could build
A quality control software platform that pairs with standard eye-tracking hardware to train AI models on expert inspector behavior, then automates or audits conformance decisions on production lines. Target buyers would be manufacturers in aerospace, electronics, or automotive sectors with high-stakes visual inspection requirements.
Who in Virginia should care
Defense and aerospace manufacturers in Northern Virginia and the Hampton Roads corridor, as well as shipbuilding and electronics manufacturers, would have immediate use for automated visual inspection systems meeting stringent conformance standards.
Readiness: Prototype likely
Concept — described but not yet demonstrated. Lab validated — supported by experimental results in the patent. Prototype likely — the text describes a built, working embodiment.
Readiness is inferred from the patent text, not from a lab visit.
The record
- Inventors
- Ran Jin, Xiaoyu Chen
- Granted
- January 14, 2025
- Status
- Granted patent
- Patent number
- 12197877
Ready to talk?
Virginia Tech Intellectual Properties handles licensing for this technology.
Prosim summaries are generated from public patent text and are not legal advice.