Our FR10 scratch examples have moving bright bands and sample numbers reused between two batches. Physical matches are uncertain.
I cannot select bezel references with reused sample numbers
JuliaChan1109 · 20 Mar 2026, 11:03 UTC
7 replies
Replying to JuliaChan1109
Recover the batch identity with each sample number before trusting the labels; otherwise the same numbered bezel may be two different parts in your folder.
19pointsReplying to JamieChan1078
Capture sheets identify both batches. The slide export dropped that field and mixed their number lists.
14pointsReplying to JuliaChan1109
Rejoin the images from the original capture sheets, then have quality confirm the physical decisions; the corrected filename won't tell you whether somebody called a reflection a scratch.
25pointsReplying to JuliaChan1109
Are the physical bezels still separated by batch?
14pointsReplying to LuisChan1130
Yes, in identified boxes. We can recover the links without guessing from the bright bands.
18pointsReplying to JuliaChan1109
Links recovered. Quality corrected one guessed scratch label; the actual rejected bezel has a separate edge defect.
12pointsReplying to JuliaChan1109
Keep that accepted bright-band example in the imaging comparison alongside the confirmed edge defect, so the next view has to handle both rather than merely look quieter.
21pointsDiscussion closed
This discussion is closed to new replies after six months without activity. Last activity: .