Initial commit: Invoice field extraction system using YOLO + OCR

Features:
- Auto-labeling pipeline: CSV values -> PDF search -> YOLO annotations
- Flexible date matching: year-month match, nearby date tolerance
- PDF text extraction with PyMuPDF
- OCR support for scanned documents (PaddleOCR)
- YOLO training and inference pipeline
- 7 field types: InvoiceNumber, InvoiceDate, InvoiceDueDate, OCR, Bankgiro, Plusgiro, Amount

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

configs/default.yaml

@@ -0,0 +1,129 @@
+# Invoice Master POC v2 Configuration
+# Default configuration for invoice field extraction system
+
+# PDF Processing
+pdf:
+  dpi: 300                    # Resolution for rendering PDFs to images
+  min_text_chars: 30          # Minimum chars to consider PDF as text-based
+
+# OCR Settings
+ocr:
+  engine: paddleocr           # OCR engine to use
+  lang: en                    # Language code (en, sv, ch, etc.)
+  use_gpu: false              # Enable GPU acceleration
+
+# Field Normalization
+normalize:
+  # Bankgiro formats
+  bankgiro:
+    format: "XXXX-XXXX"       # Standard 8-digit format
+    alternatives:
+      - "XXX-XXXX"            # 7-digit format
+
+  # Plusgiro formats
+  plusgiro:
+    format: "XXXXXXX-X"       # Standard format with check digit
+
+  # Amount formats
+  amount:
+    decimal_separator: ","    # Swedish uses comma
+    thousand_separator: " "   # Space for thousands
+    currency_symbols:
+      - "SEK"
+      - "kr"
+
+  # Date formats
+  date:
+    output_format: "%Y-%m-%d"
+    input_formats:
+      - "%Y-%m-%d"
+      - "%Y-%m-%d %H:%M:%S"
+      - "%d/%m/%Y"
+      - "%d.%m.%Y"
+
+# Field Matching
+matching:
+  min_score_threshold: 0.7    # Minimum score to accept match
+  context_radius: 100         # Pixels to search for context keywords
+
+  # Context keywords for each field (Swedish)
+  context_keywords:
+    InvoiceNumber:
+      - "fakturanr"
+      - "fakturanummer"
+      - "invoice"
+    InvoiceDate:
+      - "fakturadatum"
+      - "datum"
+    InvoiceDueDate:
+      - "förfallodatum"
+      - "förfaller"
+      - "betalas senast"
+    OCR:
+      - "ocr"
+      - "referens"
+    Bankgiro:
+      - "bankgiro"
+      - "bg"
+    Plusgiro:
+      - "plusgiro"
+      - "pg"
+    Amount:
+      - "att betala"
+      - "summa"
+      - "total"
+      - "belopp"
+
+# YOLO Training
+yolo:
+  model: yolov8s              # Model architecture (yolov8n/s/m/l/x)
+  epochs: 100
+  batch_size: 16
+  img_size: 1280              # Image size for training
+
+  # Data augmentation
+  augmentation:
+    rotation: 5               # Max rotation degrees
+    scale: 0.2               # Scale variation
+    mosaic: 0.0              # Disable mosaic for documents
+    hsv_h: 0.0               # No hue variation
+    hsv_s: 0.1               # Slight saturation variation
+    hsv_v: 0.2               # Brightness variation
+
+  # Class definitions
+  classes:
+    0: invoice_number
+    1: invoice_date
+    2: invoice_due_date
+    3: ocr_number
+    4: bankgiro
+    5: plusgiro
+    6: amount
+
+# Auto-labeling
+autolabel:
+  min_confidence: 0.7         # Minimum score to include in training
+  bbox_padding: 0.02          # Padding around bboxes (fraction of image)
+
+# Dataset Split
+dataset:
+  train_ratio: 0.8
+  val_ratio: 0.1
+  test_ratio: 0.1
+  random_seed: 42
+
+# Inference
+inference:
+  confidence_threshold: 0.5   # Detection confidence threshold
+  iou_threshold: 0.45         # NMS IOU threshold
+  enable_fallback: true       # Enable regex fallback if YOLO fails
+  fallback_min_missing: 2     # Min missing fields to trigger fallback
+
+# Paths (relative to project root)
+paths:
+  raw_pdfs: data/raw_pdfs
+  images: data/images
+  labels: data/labels
+  structured_data: data/structured_data
+  models: models
+  reports: reports