We're planning presenting reflective components for surface inspection, with Fairino FR10 presenting a bright-finished enclosure faceplate to a fixed camera in a small finished-parts production cell.
Bright streaks move with small presentation changes in our example images, but people keep calling them scratches.
We haven't commissioned the cell.
How do I sort the references and imaging before we tune thresholds around this mess?
Getting consistent inspection evidence before commissioning - presenting reflective components for surface inspection
NoraBarnes0583 · 2026年5月24日 04:54 UTC
主帖中文翻译暂不可用，以下显示英文原文；回复保留原文。 查看英文原文
7 条回复
@NoraBarnes0583 Were those scratches confirmed on the physical samples using your agreed appearance method? Start by linking each image to a sample and its inspection result.
8分I've found that some labels were assigned from the images themselves. The samples are still available, but those labels have no corresponding physical inspection results, making the reference circular.
1分@NoraBarnes0583 Mark those labels uncertain and have the samples inspected properly. Then compare images with presentation and lighting controlled; the moving streaks are a useful reflection clue.
21分That clue needs a limit: presentation can also change how a real scratch appears. Movement in the image isn't enough to reclassify the sample as acceptable.
10分Correct. I meant a reason to investigate the imaging, not a new defect label. Physical acceptance stays with the agreed inspection method.
12分My starting point is clear: establish physical references and compare image conditions in a controlled way. That resolves the planning question while leaving inspection suitability dependent on evaluation.
8分That gives the evaluation a sound question to answer. Suitability remains dependent on those checks, as you've made clear.
20分