Add containerized OCR pipeline for fuel receipts

Self-hosted, verifiable pipeline for extracting structured data (station,
date/time, price per litre, litres, discount, total) from German fuel
receipt photos: grayscale + mild bilateral filter + contrast stretch,
Tesseract OCR, then LLM structuring via a small local model (Qwen 2.5,
served by Ollama). Each step is independently runnable and inspectable
through numbered scripts against a shared tooling container.

Ollama runs as its own long-lived container (0_run_ollama.sh), separate
from the stateless per-receipt pipeline steps, so the model stays loaded
in memory between runs. Includes a containerized ground-truth batch test
(test_batch.sh) that reproduces the full pipeline over the test receipts
and reports per-field accuracy.

Targets eventual deployment on a Raspberry Pi 4 k3s cluster.

tooling-container/src/preprocess.py

@@ -0,0 +1,65 @@
+#!/usr/bin/env python3
+"""Step 1: preprocess a receipt photo for OCR.
+
+Applies a mild edge-preserving smoothing pass (to take the edge off the
+receipt's dotted security background pattern) followed by a global
+percentile-based contrast stretch. Every intermediate stage is written to
+the output directory (01_gray, 02_bilateral, 03_final) so the effect of
+each step can be inspected on its own before trusting the final image to
+OCR.
+
+Heavier processing (strong denoising, local/CLAHE contrast, unsharp
+masking) was tried and tested worse: each one amplifies the security
+background pattern into OCR noise rather than suppressing it. This
+lighter two-step version was chosen because, across a set of receipts
+that the plain-grayscale baseline OCR'd incorrectly, it recovered data
+the baseline missed and never made a previously-correct read worse.
+"""
+import argparse
+import os
+
+import cv2
+import numpy as np
+from PIL import Image, ImageOps
+
+
+def load_grayscale(path: str) -> np.ndarray:
+    img = Image.open(path)
+    img = ImageOps.exif_transpose(img).convert("L")
+    return np.array(img)
+
+
+def autocontrast(gray: np.ndarray, low_pct=2, high_pct=98) -> np.ndarray:
+    lo, hi = np.percentile(gray, (low_pct, high_pct))
+    stretched = (gray.astype(np.float32) - lo) * 255.0 / (hi - lo)
+    return np.clip(stretched, 0, 255).astype(np.uint8)
+
+
+def preprocess(path: str, out_dir: str) -> str:
+    os.makedirs(out_dir, exist_ok=True)
+
+    gray = load_grayscale(path)
+    cv2.imwrite(os.path.join(out_dir, "01_gray.png"), gray)
+
+    bilateral = cv2.bilateralFilter(gray, d=5, sigmaColor=50, sigmaSpace=50)
+    cv2.imwrite(os.path.join(out_dir, "02_bilateral.png"), bilateral)
+
+    final = autocontrast(bilateral)
+    final_path = os.path.join(out_dir, "03_final.png")
+    cv2.imwrite(final_path, final)
+
+    return final_path
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("-in", dest="in_path", required=True)
+    parser.add_argument("-out", dest="out_dir", required=True)
+    args = parser.parse_args()
+
+    final_path = preprocess(args.in_path, args.out_dir)
+    print(final_path)
+
+
+if __name__ == "__main__":
+    main()