@HanaAllen0274 Some labels came from the pictures alone. We still have the samples, but those labels aren't tied to physical inspection results. That's irritatingly circular.

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.

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.

Correct. I meant a reason to investigate the imaging, not a new defect label. Physical acceptance stays with the agreed inspection method.

Should uncertain images be treated as acceptable, or kept somewhere separate while their status is established?

Keep them explicitly undecided, with the sample link. Don't use them as confirmed examples of either class until the physical review settles them.

Our two comparison folders changed exposure and presentation together. I can't tell which change made the images look better. That comparison needs a caveat too.

@NoraAdams0148 On my inspection setup, a folder called 'better lighting' also contained easier samples. The folder name was doing a lot of unearned work.

@TheoArcher0410 The reference problem is clearer, but I still can't judge inspection performance from our example images. The physical labels and image comparisons need more work.

The remaining physical-label and comparison work explains the open judgement. Clearer uncertainty doesn't yet establish inspection performance.