Our example images keep turning shiny patches into defects (Fairino FR5)

ReeceBennett0732 · 3 Sept 2026, 18:04 UTC

Reply to discussion
RE
ReeceBennett0732
We're planning checking cosmetic metal surfaces with a fixed camera, with Fairino FR5 presenting a polished metal cover to a fixed camera in a robot-presented camera station. 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?

8 replies

EL
ElliotAdams0161
Replying to ReeceBennett0732

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.

20 points
RE
ReeceBennett0732
Replying to ElliotAdams0161

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.

20 points
EL
ElliotAdams0161
Replying to ReeceBennett0732

@ReeceBennett0732 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.

23 points
TO
TomMill
Replying to ElliotAdams0161

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

7 points
EL
ElliotAdams0161
Replying to TomMill

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

15 points
CA
CallumChan1056
Replying to ElliotAdams0161

@ElliotAdams0161 So uncertain isn't the same as good? Where do those images go?

16 points
EL
ElliotAdams0161
Replying to CallumChan1056

@CallumChan1056 Keep them explicitly undecided, with the sample link. Don't use them as confirmed examples of either class until the physical review settles them.

18 points
RE
ReeceBennett0732
Replying to ElliotAdams0161

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.

7 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.