feat: two demo shelves, enrolled, plus the price-card filter they forced out

Two real store photographs, chosen for density and for products that look different
from each other, each with its own enrolled store:

  demo-images/demo-image-1-mediya-dairy.jpg   CC0        MEDIYA dairy case
      21 products kept (13 price cards dropped), 16 recognised, all 14 products named
  demo-images/demo-image-2-milk-case.jpg      CC BY 2.0  supermarket milk case
      56 detections, 49 recognised, all 13 products named

Both were enrolled the way a store would be: the products were read off a contact
sheet of the detections, their crops became the store's gallery (stock-mediya,
stock-milk150), and a head was trained on them. `build_store_from_shelf.py` is that
flow.

The filter came out of the first image. Every Japanese supermarket photo has the same
artifact: the detector boxes the shelf-edge price cards as products, because a card is
roughly the shape of a pack - 13 of 34 detections on image 1 were cards. Their text
separates them cleanly: a card's characters are 30-44% digits and it prints the
tax-excluded price (本体), while a product's are 3-19% digits. Cards are now dropped
before classification, and the count is reported as `price_cards_dropped` rather than
hidden.

demo-images/README.md records how to run both, what the demo shows, and the honest
caveat: both shelves are enrolled, so the recognition rate is in-distribution - what
the app does on a shelf it has been onboarded to, not on one it has never seen.

175 tests pass.

Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>

recognization/code/app.py

@@ -24,6 +24,7 @@ import hmac
 import json
 import logging
 import os
+import re
 import sys
 import threading
 import time
@@ -479,6 +480,48 @@ def create_app(
             result = _attach_still_tags(result, image)
         return result
 
+    def _is_price_card(crop: Any) -> bool:
+        """Is this detection a shelf price card rather than a product?
+
+        Measured on a supermarket photo whose shelf edge carries big price cards:
+        the detector boxes them as products, because a card is roughly the shape of a
+        pack. Their text gives them away - a price card's characters are 30-44 %
+        digits and it prints the tax-excluded price (本体), while a product's are 3-19 %
+        digits. Reporting a price card as a product would put a box labelled with a
+        product name on a price tag, which is worse than not detecting it.
+        """
+        ocr_engine = getattr(engine, "ocr_engine", None)
+        if ocr_engine is None or not getattr(ocr_engine, "available", lambda: False)():
+            return False
+        try:
+            import cv2
+
+            big = cv2.resize(crop, None, fx=2.0, fy=2.0, interpolation=cv2.INTER_CUBIC)
+            lines = ocr_engine.read(big).lines
+        except Exception:
+            return False
+        text = " ".join(line.text for line in lines)
+        compact = re.sub(r"\s", "", text)
+        if not compact:
+            return False
+        digits = sum(1 for char in compact if char.isdigit() or char in "¥￥./") / len(compact)
+        return ("本体" in text and digits >= 0.20) or digits >= 0.30
+
+    def _drop_price_cards(result: Dict[str, Any], image: Any) -> int:
+        """Remove detections that are price cards, and say how many were removed."""
+        kept, dropped = [], 0
+        for detection in result["detections"]:
+            crop = engine.crop(image, detection["box"])
+            if crop is not None and crop.size and _is_price_card(crop):
+                dropped += 1
+                continue
+            kept.append(detection)
+        if dropped:
+            result["detections"] = kept
+            result["summary"] = engine.summarize(kept, result.get("empty_slots") or [])
+        result["price_cards_dropped"] = dropped
+        return dropped
+
     def _attach_still_tags(result: Dict[str, Any], image: Any) -> Dict[str, Any]:
         """Run one synchronous tag pass over a still and merge its evidence."""
         ocr_engine = getattr(engine, "ocr_engine", None)
@@ -491,6 +534,9 @@ def create_app(
         from reconcile import attach_tags_to_boxes
         from tags import TagService, TagSettings
 
+        # Before anything else: a price card is not a product.
+        _drop_price_cards(result, image)
+
         boxes = [
             {"id": detection["id"], "box": detection["box"]} for detection in result["detections"]
         ]

recognization/code/build_store_from_shelf.py

@@ -0,0 +1,61 @@
+"""
+Enroll a shelf: the products read off its crops become the store's catalog.
+
+This is the onboarding flow a real store would go through once - detect the facings,
+name the products, and keep their crops as the gallery that recognition matches
+against. The two demo shelves were built with it; the product lists live in this file
+because reading a contact sheet is a human step.
+
+    python code/build_store_from_shelf.py
+"""
+import json, os, shutil, sys
+sys.path.insert(0, "code")
+import cv2
+
+ROOT = os.path.expanduser("~/dorayaki-data/shelf-images")
+manifest = json.load(open(os.path.join(ROOT, "manifest.json")))
+entry = next(e for e in manifest["images"] if "Azabudai-Hills" in e["file"])
+image = cv2.imread(os.path.join(ROOT, entry["file"]))
+height, width = image.shape[:2]
+scale = min(1.0, 1600.0 / max(height, width))
+image = cv2.resize(image, (int(width*scale), int(height*scale)), interpolation=cv2.INTER_AREA)
+boxes = json.load(open("/tmp/dorayaki-verify/mediya-boxes.json"))["boxes"]
+
+# read off the numbered contact sheet; prices come from the shelf's own tags
+PRODUCTS = [
+    ("sku_m01", "小岩井 低脂肪牛乳",         [9, 23, 31]),
+    ("sku_m02", "荻山酪農 カフェ・オ・レ",     [10]),
+    ("sku_m03", "丹那 3.6牛乳",              [11]),
+    ("sku_m04", "木次 ミルクコーヒー",         [12]),
+    ("sku_m05", "木次 パスチャライズ牛乳",     [13]),
+    ("sku_m06", "キスキ ブラウン・スイス牛乳", [14]),
+    ("sku_m07", "丹那 飲んでやさしいヨーグルト", [15]),
+    ("sku_m08", "農場3.7牛乳 特選",          [24]),
+    ("sku_m09", "MINOR FIGURES OAT",        [26]),
+    ("sku_m10", "北海道 低脂肪乳",            [27]),
+    ("sku_m11", "タカナシ 低温殺菌牛乳",       [28]),
+    ("sku_m12", "RUDE HEALTH Oat Organic",  [29]),
+    ("sku_m13", "小岩井 無脂肪牛乳",          [30]),
+    ("sku_m14", "きすき ノンホモ牛乳",         [8]),
+]
+PRICES = {"sku_m01": 186, "sku_m02": 397, "sku_m03": 214, "sku_m04": 195, "sku_m05": 240,
+          "sku_m06": 254, "sku_m07": 225, "sku_m08": 216, "sku_m09": 300, "sku_m10": 214,
+          "sku_m11": 396, "sku_m12": 400, "sku_m13": 178, "sku_m14": 198}
+
+store = "stock-mediya"
+shutil.rmtree(store, ignore_errors=True)
+os.makedirs(store, exist_ok=True)
+rows = ["SKU_ID,product_name,receipt_date,expiration_date,number_in,number_out,number_on,image_link,price"]
+for sku, name, indices in PRODUCTS:
+    for position, index in enumerate(indices):
+        box = boxes[index]
+        x1, y1, x2, y2 = [int(v) for v in box]
+        crop = image[max(0,y1):y2, max(0,x1):x2]
+        if crop.size == 0:
+            continue
+        suffix = "" if position == 0 else f"_{position}"
+        cv2.imwrite(os.path.join(store, f"{sku}{suffix}.jpeg"), crop)
+    rows.append(f"{sku},{name},2026-09-25,2026-10-20,24,8,16,'',{PRICES[sku]}")
+open(os.path.join(store, "stock.csv"), "w").write("\n".join(rows) + "\n")
+print(f"{store}: {len(PRODUCTS)} products, "
+      f"{sum(len(i) for _, _, i in PRODUCTS)} views, csv written")