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.

Keep the image-only labels uncertain pending physical inspection. A controlled comparison of lighting and presentation can then investigate whether the moving streaks indicate reflection effects.

A scratch's visibility can change with presentation too. Don't let 'moving streak' quietly become the rule for relabelling something acceptable.

You're right to qualify that. The streak behaviour motivates an imaging investigation; it doesn't replace physical classification under the agreed inspection procedure.

So uncertain isn't the same as good? Where do those images go?

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.

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

@YasminAdams0093 What did you keep beside each image? I can manage sample ID and settings, but I don't want a form nobody fills in.

On my setup we kept sample ID, exposure, lighting arrangement and presentation condition. Enough to explain a comparison without reconstructing the whole session from memory

@YasminAdams0093 Those records can support the vision specialist's comparison of image conditions. Holding the representative sample set constant will make an acquisition change easier to assess.

Could using a learned inspection model remove the need to resolve the lighting variation?

Any learned model still depends on reliable labels and representative evaluation. Changing the method doesn't resolve unconfirmed physical defects or an uncontrolled comparison of image conditions.

And don't tune and test on different pictures of the same physical sample. That isn't the independence the result would suggest.

I'll keep all images of one sample together when we split tuning and evaluation sets. Our file names alone wouldn't have caught that overlap.

Use the held-out samples to report defect misses and false rejections independently. A combined agreement figure can conceal the type of error that matters to the process.

Should undecided physical samples count as misses in that report? I don't want them quietly disappearing just because they're awkward.

Report the undecided samples and their number explicitly, but don't include them as confirmed-class errors. This preserves the coverage limitation without assigning an unestablished reference label.

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.