ninja_hippo/card-grader
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Stop telling the model to give up on corners/edges just for being in a holder

Browse source 
The framing caveat added earlier told the model to find the card's real
edge inside each mis-cut crop, then immediately offered 'say cannot_assess
if the close-up doesn't clearly contain it' — wrapped in alarming language
about cases. On a Fleer Ultra Jordan shot in a clear toploader it took the
escape hatch for corners AND edges, returning three of four categories as
'can't tell from photo' on a card whose corners are plainly visible through
the plastic. That was a regression I introduced, not a limit of the photo.

A toploader is transparent: corner sharpness, corner whitening, edge
chipping and edge whitening all read through it, and the card's cut line is
visible as a distinct boundary inside the holder's (confirmed in the pixel
profile — the card's own edge shows as a clear step ~75px inside the
detected holder boundary). Those categories now get judged normally, with
cannot_assess reserved for genuinely hidden geometry.

Surface keeps the escape hatch, because there it's correct: scratches, dust
and glare on a holder sit directly over the card's surface and can't be
separated from it in a photo.
This commit is contained in:
Barely Removable 2026-08-25 08:30:39 -07:00
parent 811c16f334
commit 3510f637ba
1 changed files with 26 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

38
vision.py
View file

@ -1001,18 +1001,32 @@ def grade_card(images, api_key=None, model=None, effort=None, zoom_details=True)
"read resampling softness as card wear.") "read resampling softness as card wear.")
if framing: if framing:
prompt_parts.append( prompt_parts.append(
"IMPORTANT CAVEAT ON THOSE CROPS: {} Because the crop " "CAVEAT ON THOSE CROPS: {} The crop rectangle comes from that "
"rectangle is derived from that same detection, each close-up " "same detection, so each close-up is cut against the wrong "
"is cut relative to the wrong boundary — a corner close-up may " "boundary — most often because the card is in a toploader, "
"well be showing the CORNER OF A CASE, SLEEVE OR HOLDER with " "sleeve or case and the detection found the HOLDER's outline "
"the card's own corner sitting somewhere inside the frame, or " "instead of the card's. The card's own corner or edge is "
"out of it. Do not assume the crop's own edge is the card's " "therefore sitting inside the frame rather than at the crop's "
"edge. Find the actual card edge inside each close-up first " "own corner. Locate it and judge that.\n"
"and judge only that; if a given close-up doesn't clearly " "Being in a holder is NOT by itself a reason to give up on "
"contain the card's real corner or edge, say cannot_assess " "corners or edges. A toploader or penny sleeve is clear "
"for that category rather than grading the holder. Damage, " "plastic: corner sharpness, corner whitening, edge chipping "
"scuffing or whitening on a case is not damage to the " "and edge whitening all read straight through it, and the "
"card.".format(framing)) "card's cut line is normally plainly visible as a distinct "
"boundary inside the holder's. Judge those categories "
"normally — just make sure you are reading the CARD's "
"boundary and not the holder's, and never count scuffing, "
"scratching or whitening that belongs to the plastic as "
"damage to the card. Reserve cannot_assess for a corner or "
"edge genuinely hidden — obscured by a label, blown out by "
"glare, or out of frame — not merely for being behind clear "
"plastic.\n"
"SURFACE is the real exception. Scratches, dust, haze and "
"glare on a holder sit directly over the card's own surface "
"and cannot be separated from it in a photo, so "
"cannot_assess IS the honest answer for surface on a card "
"shot through a scratched or dusty holder — say so plainly "
"and name the holder as the reason.".format(framing))
prompt_parts.append("Estimate the PSA grade this trading card would likely receive.") prompt_parts.append("Estimate the PSA grade this trading card would likely receive.")
parsed, usage = _call_vision( parsed, usage = _call_vision(