Our FR5 cover comparison needs more than withdrawing the guessed labels

SarahBell0676 · 30 Jul 2026, 18:35 UTC

Reply to discussion
SA
SarahBell0676
I've removed guessed labels from a faceplate tuning set before, while preserving the disputed images. This planned FR5 polished-cover station has the same moving-streak problem. How should I organise physical decisions and repeatable imaging together so we don't simply build another uncertain set?

16 replies

ME
MeiAbbott0081
Replying to SarahBell0676

Keep one identity for each physical cover across inspection and capture records. Have the appearance owner judge the surface under the agreed method, while recording the presentation and imaging conditions independently of that judgement.

6 points
SA
SarahBell0676
Replying to MeiAbbott0081

We retained the selected covers. I can establish those links; the wider image folder has weaker identities and isn't going into tuning just because it is larger.

13 points
NO
NoraBrown0931
Replying to SarahBell0676

Make the capture comparison repeatable before expanding it. Same identified covers, declared holder and lighting, then deliberate presentation cases. Changing lamp, seating and exposure together leaves you with another argument about what helped.

6 points
JO
JoBrown0940
Replying to NoraBrown0931

Include whoever normally loads the holder, not just the person designing it.

9 points
AM
AmaraBell0687
Replying to NoraBrown0931

Does the holder have an observable seating reference, or are people judging by the outline?

8 points
SA
SarahBell0676
Replying to AmaraBell0687

Mostly by the outline. The fixture person is identifying the intended contacts before we define repeat placement cases.

22 points
ME
MeiAbbott0081
Replying to SarahBell0676

Keep that as an observation about the current method, not a proven cause. Physical surface decisions can proceed while the holder review establishes which presentation differences to compare.

20 points
NO
NoraBrown0931
Replying to MeiAbbott0081

Yes. Don't wait for a perfect holder to discover your supposed scratch reference has never been physically judged.

13 points
JO
JoBrown0940
Replying to MeiAbbott0081

Will uncertain covers remain available after the first review?

0 points
SA
SarahBell0676
Replying to JoBrown0940

They will. Quality has classified the selected covers and left one faint feature unresolved. It stays identified outside the tuning targets, not discarded.

5 points
AM
AmaraBell0687
Replying to SarahBell0676

And the holder comparison? Curious whether the intended contacts explain the repeat placements.

11 points
SA
SarahBell0676
Replying to AmaraBell0687

Existing placements use the contacts inconsistently. Fixture review is proposing a clearer seating arrangement; no revised capture results yet.

13 points
ME
MeiAbbott0081
Replying to SarahBell0676

Use both confirmed acceptable and rejected references in that revised comparison. Improved seating is useful only if the required surface features remain visible across the intended presentation range.

22 points
NO
NoraBrown0931
Replying to MeiAbbott0081

Keep validation selection separate from the images used to tune. Otherwise the team may only prove it can reproduce decisions on its familiar small set.

4 points
SA
SarahBell0676
Replying to JoBrown0940

Quality is selecting that separately. Thanks Jo, the regular loader is reviewing the proposed seating arrangement, so its explanation won't depend on me being beside the bench.

18 points
JO
JoBrown0940
Replying to SarahBell0676

Come back with what they find awkward. A contact drawing can still leave a very ordinary loading question unanswered.

21 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.