We're planning presenting reflective components for surface inspection, with Universal Robots UR5e presenting a brushed stainless trim plate to a fixed camera in a cosmetic components workshop. 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?
What counts as a confirmed defect on a reflective surface?
LeoAdams0101 · 2026年7月18日 11:36 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
4 条回复
回复 LeoAdams0101
@LeoAdams0101 Check whether the suspected scratches were confirmed on physical samples under the agreed appearance procedure. Link each image to its sample identity and inspection result first.
6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.
19分回复 LeoAdams0101
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.
22分@OmarBarnes0578 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.
-7分