I found the same trim plate in both the clean and scratch folders. Different captures, same little mark on the back. We're planning FR10 presentation to a camera and people have been sorting cropped images by how convincing the bright line looks.
I can trace this pair back to the plate. Several other crops have no usable identity left. I'd rather lose some training examples than pretend those labels are settled, but am I throwing away useful lighting examples too?
Keep them as lighting examples with the uncertain labels removed; no reason to delete a useful picture just because somebody put it in the wrong teaching folder.
I had to reconnect crops to full views in my own comparison. Can you recover the full frames here? The back mark is useful, but I'd still want the original file pair before calling those two images a match.
The capture sheet has front and back photos under each plate number. These two still have file names that join to that sheet. The others were renamed for a presentation.
Theo, yes, the two identified captures have full frames on the capture machine. Same plate number and back photo in both entries. Its condition still needs checking.
Sam, I agree about identity. The full frame helped me find a crop that had been taken from the wrong end of a part. It didn't tell me whether the surface was acceptable.
Noah's suggestion recovered wider pictures from the slides, but no dependable plate numbers. Those are now in a separate lighting discussion folder. Nothing from that folder goes into the labelled export.
Glad the slides yielded something. Were both supposedly opposite labels attached to the same area of the plate, or were they describing different areas?
Same area, Noah. Quality checked the identified plate and accepted that area under the agreed physical inspection method. The line in one capture is conspicuous, which is why somebody promoted it to scratch without looking.
That accepted example is useful. Have you got a physically rejected mark in the same region to compare? My nice clean examples stopped being informative once we added a different finish.
Quality owns the surface decision and I've taken ownership of joining that decision to the image files. Nobody is meant to judge a part from the slide thumbnails. That instruction was missing before.
Theo, we have a rejected plate with a physical mark in that region. Its image pair is being made under the same recorded setup; I won't quietly borrow one from the old mystery pile.
The new pair is back. Our present view makes the accepted streak stronger than the real rejected feature, so the team dropped the proposed brightness cutoff. We're trying a revised lighting arrangement on identified plates; the image folders are repaired, the inspection method isn't finished.