vnguyen/product-recognition-demo
1
0
Fork 1
Code Issues Pull requests 1 Projects Releases Packages Wiki Activity Actions

fix(identity): calibrate both accept lines against unrelated shelves

Browse source 
The gates were tuned on image6 alone, where every crop is a facing of a product
the shelf actually holds. Wikimedia supermarket photos of milk, soy and snack
shelves share nothing with the LOPIA catalog, so every accept there is a false
accept by construction - and at the old lines there were 83 of them.

Text lane: TEXT_MIN_SHARED 2 -> 4. The vocabulary filter drops bigrams no name
contains, so a short garbage read can end up with a perfect ratio on two
coincidental pairs. 20 of 26 text-lane answers on those shelves rested on
exactly two: '避くて おいしい' named sku_l12 through おい/いし.

Local lane: LOCAL_ACCEPT 2.0 -> 4.0. The residual accepts were geometric
matches with no text overlap at all, scoring 2.26-4.81.

Measured, 2297 distractor crops and 109 image6 facings:
  accept  floor   image6 shown/correct   precision   false accepts
  2.0     2       54 / 49                90.7%       83 (3.61%)
  2.0     4       52 / 48                92.3%       30 (1.31%)
  4.0     4       44 / 42                95.5%        8 (0.35%)
  5.0     6       36 / 36               100.0%        0 (0.00%)

4.0/4 is the only region passing both G2 (>=95% precision) and G3 (<=1%
far-unknown) with coverage left. On the shipped evaluator: 66% end-to-end at
95% precision, 2 false accepts, against 77%/91%/5 before.

The two tests that pinned the old floors now pin the new ones, with the reads
that separate them.
This commit is contained in:
kiyo9w 2026-09-29 04:08:59 +09:00
parent d13ce94123
commit 07de2bd37d
4 changed files with 166 additions and 22 deletions
Download patch file Download diff file Expand all files Collapse all files

7
recognization/code/identity.py
View file

@ -30,8 +30,11 @@ DEFAULT_MIN_CONFIDENCE = 0.55
# `local` scale (identity_lanes.LocalLane). The value is already a margin over
# the runner-up, so the relative-margin test does not apply to it: a single
# absolute line is the whole gate.
LOCAL_ACCEPT = 2.0
# absolute line is the whole gate. Kept equal to identity_lanes.LOCAL_ACCEPT,
# which is what the engine's DecisionPolicy uses; this copy exists for the
# evaluator's `--no-text` path, and two different lines would score the same
# crops two ways.
LOCAL_ACCEPT = 4.0
def relative_confidence(top_score: float, runner_up_score: float) -> float: