Our example images keep turning shiny patches into defects

LinAllen0270 · 6 Aug 2026, 15:39 UTC

Reply to discussion
LI
LinAllen0270
Our planned inspecting reflective surfaces for scratches in a small finished-parts production cell has Universal Robots UR5e presenting a reflective aluminium bezel 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.

15 replies

RE
RebeccaAllen0343
Replying to LinAllen0270

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.

14 points
LI
LinAllen0270
Replying to RebeccaAllen0343

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.

10 points
RE
RebeccaAllen0343
Replying to LinAllen0270

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.

20 points
AN
AnikaAli0247
Replying to RebeccaAllen0343

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.

0 points
RE
RebeccaAllen0343
Replying to AnikaAli0247

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

23 points
FE
FelixBaker0458
Replying to RebeccaAllen0343

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

25 points
RE
RebeccaAllen0343
Replying to FelixBaker0458

Retain their sample identities and undecided status. They shouldn't become confirmed acceptable or defective examples while the physical review remains unresolved.

7 points
LI
LinAllen0270
Replying to RebeccaAllen0343

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.

-1 points
NA
NadiaArcher0378
Replying to LinAllen0270

@LinAllen0270 I had a separate inspection setup where the 'better lighting' folder used easier samples too. Its name implied a lighting conclusion that the comparison didn't support.

10 points
LI
LinAllen0270
Replying to NadiaArcher0378

@NadiaArcher0378 Which details did you retain with each image? I can record sample identity and settings, but I'd like a practical record people will actually maintain.

5 points
NA
NadiaArcher0378
Replying to LinAllen0270

For my separate setup, sample identity, exposure, lighting arrangement and presentation condition were the useful essentials. They let us understand comparisons without relying on recollection.

13 points
RE
RebeccaAllen0343
Replying to NadiaArcher0378

@NadiaArcher0378 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.

17 points
FE
FelixBaker0458
Replying to RebeccaAllen0343

Would a learned model just cope with the lighting differences?

14 points
RE
RebeccaAllen0343
Replying to FelixBaker0458

It still needs trustworthy labels and representative evaluation. A different model doesn't establish whether your reference scratches are real or your acquisition comparison is fair.

13 points
AN
AnikaAli0247
Replying to RebeccaAllen0343

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

12 points

Add to the discussion

Welcome to Application Robot

Everyone can read the forum. Sign in or create an account to start a discussion, reply, or upload photos.

Forgot your password?

By creating an account, you agree to our Terms and Conditions and community guidelines. Read our Privacy Policy for how your information is handled.