Machine Vision & Industrial Inspection AI worked example

AI Inspection Precision Recall at 99% required detection recall specification: a worked example

This scenario runs the ai inspection precision recall calculation on the strong side: 99% required detection recall specification, with every other input held at its documented default. Use it when validating an AI inspection model against a known-defect sample set and you need to calculate and document detection recall before releasing the model to production.

The inputs for this scenario

  • True positives (defects correctly detected): 96 defects (unchanged)
  • Total actual defects in validation sample: 100 defects (unchanged)
  • Required detection recall specification: 99 % (raised for this scenario; the documented default is 98)

Working through the calculation

  • Applying the documented formula (Recall = true positives / total actual defects x 100) to the inputs above produces each figure below.
  • At this operating point the engine returns 96 % for ai model recall (detection rate), the number this scenario is built around.
  • At this operating point the engine returns 3 points for gap to required recall specification.
  • At this operating point the engine returns 96 count for true positives detected.
  • At this operating point the engine returns 100 count for total actual defects in sample.

How this compares with the baseline

  • Against the tool's baseline example, where required detection recall specification sits at 98% and the headline result is 96 %, this scenario lands almost exactly on the baseline at 96 %.
  • Use it when validating or auditing an AI defect-detection model against an escape-rate target before or during production deployment. Treat this as a target state: the delta against the baseline quantifies what the improvement is worth before you commit to chasing it.

Results at a glance

  • AI model recall (detection rate): 96 % (headline result)
  • Gap to required recall specification: 3 points
  • True positives detected: 96 count
  • Total actual defects in sample: 100 count

Run it with your numbers

  • Every input above is editable in the live AI Inspection Precision Recall calculator, which recalculates instantly and can be shared with the inputs intact.

Last reviewed 2026-05-12.