A fixed camera, small presentation changes, very different streaks - planning camera inspection of reflective parts

SaraAli0200 · 28 Aug 2026, 14:16 UTC

Reply to discussion
SA
SaraAli0200
We're planning planning camera inspection of reflective parts, with Fairino FR10 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?

10 replies

IS
IsaacAdams0172
Replying to SaraAli0200

@SaraAli0200 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.

3 points
SA
SaraAli0200
Replying to IsaacAdams0172

@IsaacAdams0172 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.

19 points
IS
IsaacAdams0172
Replying to SaraAli0200

@SaraAli0200 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.

13 points
AN
AnikaAli0247
Replying to IsaacAdams0172

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.

1 points
IS
IsaacAdams0172
Replying to AnikaAli0247

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

18 points
LU
LuisBrown0956
Replying to IsaacAdams0172

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

23 points
IS
IsaacAdams0172
Replying to LuisBrown0956

@LuisBrown0956 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
SA
SaraAli0200
Replying to IsaacAdams0172

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.

2 points
SA
SaraAli0200
Replying to SaraAli0200

My starting point is clear: establish physical references and compare image conditions in a controlled way. That resolves the planning question while leaving inspection suitability dependent on evaluation.

3 points
IS
IsaacAdams0172
Replying to SaraAli0200

You've settled the starting method, with inspection suitability still tied to the physical-reference and controlled-image evaluation.

14 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.