52905e73f6
Stage 2 of the plan is "identity as retrieval", so the first thing measured was whether retrieval can even work here. It cannot, on its own: an off-the-shelf DINOv2 embedding does group identical products (two orange juices, two apple juices, two almond drinks) but the fine-grained cases collapse - 32 cartons into one cluster, and nine different bottled drinks grouped by *container shape*. That matches the literature (RP2K, RPC all fine-tune; nobody ships off-the-shelf features for SKU identity). Meanwhile the shelf has been carrying the answer. Every product has a tag printed under it, and the tag spells the product's name out in clean text, once per product - the store's own label. This adds that as an identity channel: - a tag with a readable name is matched against the catalog by name similarity; - facings are assigned to the *nearest tag along their row* (the tags mark where products sit), not by geometric grouping, which was measured to merge different products into a 945 px "product" that then swallowed the wrong tag; - rows are clustered first, because the same column on six shelves would otherwise become one product. Then the demo catalog itself had to be fixed: it listed another store's products (senbei, Tropicana) while the shelf holds mayonnaise, so nothing could match. The catalog for this shelf was read off the tags - 12 products with names and prices - and the products were enrolled as packaging templates by cropping the facings the tags had just named. Measured through the real still path on add/image6.jpg (111 detections): tag named the product 28 facings (all 28 verified correct by eye) packaging named the product 74 facings both spoke 23 facings, agreeing 16 (69 %) facings with any identity 79 So packaging recognition makes a ~30 % error rate on the facings the tag can check, and every disagreement carried a low packaging score. The tag therefore wins a conflict, and the conflict is recorded (`identity_conflict`) instead of hidden - a product whose tag says one thing and whose packaging says another is a real finding, not noise to suppress. 144 tests pass; test_tag_identity.py adds 6. Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
1.2 KiB
1.2 KiB
| 1 | SKU_ID | product_name | receipt_date | expiration_date | number_in | number_out | number_on | image_link | price |
|---|---|---|---|---|---|---|---|---|---|
| 2 | sku_l01 | キューピー エッグケア 305g | 2026-09-18 | 2026-12-20 | 36 | 12 | 24 | '' | 349 |
| 3 | sku_l02 | キューピー アマニ油マヨネーズ 200g | 2026-09-18 | 2026-12-20 | 24 | 9 | 15 | '' | 329 |
| 4 | sku_l03 | キューピー からしマヨネーズ 200g | 2026-09-18 | 2026-12-20 | 30 | 14 | 16 | '' | 219 |
| 5 | sku_l04 | やまや めんたいマヨネーズタイプ 200g | 2026-09-18 | 2026-11-30 | 18 | 6 | 12 | '' | 399 |
| 6 | sku_l05 | キューピー ゼロ ノンコレステロール 310g | 2026-09-20 | 2026-12-25 | 24 | 11 | 13 | '' | 269 |
| 7 | sku_l06 | キューピー フィッテ 210g | 2026-09-20 | 2026-12-25 | 18 | 7 | 11 | '' | 379 |
| 8 | sku_l07 | 丸和油脂 ラッキーマヨネーズ 200g | 2026-09-20 | 2026-12-25 | 24 | 10 | 14 | '' | 199 |
| 9 | sku_l08 | スパイシーストーム ペリペリミックス 30g | 2026-09-15 | 2027-03-15 | 12 | 4 | 8 | '' | 699 |
| 10 | sku_l09 | ピュアセレクト コクうま カロリーカット65% 360g | 2026-09-22 | 2026-12-28 | 30 | 13 | 17 | '' | 209 |
| 11 | sku_l10 | ピュアセレクト マヨネーズ 450g | 2026-09-22 | 2026-12-28 | 36 | 15 | 21 | '' | 222 |
| 12 | sku_l11 | キューピー ハーフマヨネーズ 450g | 2026-09-19 | 2026-12-22 | 48 | 22 | 26 | '' | 269 |
| 13 | sku_l12 | 焼肉のたれ 中辛 | 2026-09-10 | 2027-02-10 | 24 | 8 | 16 | '' | 299 |