Our planned inspecting reflective surfaces for scratches in a small finished-parts production cell has Fairino FR10 presenting a brushed stainless trim plate to a fixed camera.
The example images contain bright streaks that shift with small presentation differences, yet those streaks are being labelled as scratches.
Before commissioning, I'd like to establish reliable references and image conditions for threshold tuning.
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.
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.
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.
@LeahAli0234 Keep them explicitly undecided, with the sample link. Don't use them as confirmed examples of either class until the physical review settles them.
I've checked the image folders and found that exposure and presentation both changed between them. Their improved appearance can't be attributed to either change individually.
@LinAllen0270 On my inspection setup, a folder called 'better lighting' also contained easier samples. The folder name was doing a lot of unearned work.
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.
Use those details to ask your vision specialist for controlled comparisons on representative surfaces. Keep the sample set fixed when assessing an acquisition change.
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.