feat: add VIN photo OCR pipeline (refs #67)

Implement VIN-specific OCR extraction with optimized preprocessing:

- Add POST /extract/vin endpoint for VIN extraction
- VIN preprocessor: CLAHE, deskew, denoise, adaptive threshold
- VIN validator: check digit validation, OCR error correction (I->1, O->0)
- VIN extractor: PSM modes 6/7/8, character whitelist, alternatives
- Response includes confidence, bounding box, and alternatives
- Unit tests for validator and preprocessor
- Integration tests for VIN extraction endpoint

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

ocr/app/models/schemas.py

@@ -21,6 +21,36 @@ class ExtractedField(BaseModel):
     confidence: float = Field(ge=0.0, le=1.0)
 
 
+class BoundingBox(BaseModel):
+    """Bounding box for detected region."""
+
+    x: int
+    y: int
+    width: int
+    height: int
+
+
+class VinAlternative(BaseModel):
+    """Alternative VIN candidate."""
+
+    vin: str
+    confidence: float = Field(ge=0.0, le=1.0)
+
+
+class VinExtractionResponse(BaseModel):
+    """Response from VIN extraction endpoint."""
+
+    success: bool
+    vin: Optional[str] = None
+    confidence: float = Field(ge=0.0, le=1.0)
+    bounding_box: Optional[BoundingBox] = Field(default=None, alias="boundingBox")
+    alternatives: list[VinAlternative] = Field(default_factory=list)
+    processing_time_ms: int = Field(alias="processingTimeMs")
+    error: Optional[str] = None
+
+    model_config = {"populate_by_name": True}
+
+
 class OcrResponse(BaseModel):
     """Response from OCR extraction."""