AnikaBennett0769 · 9 Apr 2025, 04:48 UTC
Find that actual cover first. We wasted a morning arguing over reflections on a part nobody had kept. Can the person who labelled it show you the supposed scratch on the surface?
20 pointsCover is still here, happily. Nobody marked the area, and the person who labelled the folder was judging from the images rather than inspecting it
14 pointsRight, so those labels are opinions about pictures. I'd have quality inspect the cover and record any actual defect location before using either image as a tuning reference.
8 pointsWho defines an unacceptable scratch for this product? Identifying a surface feature and deciding that it fails the appearance requirement are separate decisions.
12 pointsQuality should answer that too. Sorry, I skipped from finding a mark to calling it a defect. There may be allowed surface features we need the camera to ignore.
20 pointsAnd hold the presentation still. Moving the cover changes the lighting you're arguing about.
4 pointsAgreed, but I'd keep a few controlled pose variations in the trial as well. We need to know what happens when the presentation isn't perfectly repeated, not only get one flattering image.
15 pointsQuality found no scratch at the bright line's location. There is a small edge scuff elsewhere. We've recorded both, and neither original folder label tells that story
19 pointsRetain the corrected explanation with the images so a future trainer does not accidentally restore the old labels when rebuilding the dataset.
23 pointsDone. Old labels remain in the audit history, excluded from our reference set. Next question is how much pose variation our fixture actually permits
18 pointsUse that permitted variation in the training examples, with quality's decision attached, so an operator can distinguish an uncertain image from an accepted surface condition.
5 pointsNice to have the physical cover settle one part of the argument. Are you measuring the presentation variation, or is that still someone wiggling it by eye? We started with the latter and got very creative results.
14 pointsMeasure the seating repeatability first. My 'hold it still' reply made that sound easier than it is.
6 pointsA simple repeat-seating study should give the fixture and imaging people something shared to work from. Let them define the method; otherwise a camera change could hide a seating problem you're meant to fix.
10 pointsHas quality confirmed whether the edge scuff is acceptable? The bright reflection is now explained, but that second feature still needs a disposition before the cover becomes a labelled reference.
18 pointsThis discussion is closed to new replies after six months without activity. Last activity: .