All applications

06 · Contamination

Something that shouldn't be there.

Detecting foreign objects, dirt and surface deviations — inherently the most unpredictable scenario, since contamination can take almost any shape.

Unlike defects with a repeatable character (like a specific missing component), contamination is by definition irregular — dust, a fibre, a chip, a stain. Here the model learns the pattern of a "clean", correct surface and detects deviation from it, rather than recognising one specific, known defect shape.

This approach works well where the product surface is uniform enough for the deviation to stand out against the background. Where the material texture itself is naturally variable, the line between "normal variation" and "contamination" needs a clearly agreed threshold — and that is exactly what we set before the pilot.

The size of contamination that can be detected depends directly on camera resolution and field of view relative to product size — so assessing camera and optics is the first qualification step here.

When this scenario usually works well

  • 01 The product surface is uniform enough for contamination to contrast against the background
  • 02 The minimum contamination size that matters is visible at the available camera resolution
  • 03 Examples of typical contamination from the real process exist, not only artificially placed samples
  • 04 A threshold is defined — how large or numerous contamination still qualifies the product as OK

What the pilot report shows

Because contamination is inherently irregular, validation focuses especially on how the model handles borderline cases — minor deviations close to the agreed threshold — not only obvious defects.

How this works in practice

AIVQC TrainerAIVQC ServerAIVQC Production

FAQ

Contamination

Can AIVQC tell contamination apart from natural material variation?+

That depends on the contrast between them in the available images — exactly what the pilot assesses before a GO or NO-GO recommendation.

Can very small contamination, like a single fibre, be detected?+

That depends on camera resolution and field of view relative to product size. If the current hardware cannot support it, the pilot report will flag it as a limitation to consider.