Full-Field UK Vehicle Registration (V5C Logbook) OCR

The Challenge: Multi-Page Layouts and Perspective Distortion

The UK V5C Logbook is a notoriously difficult document for automated data extraction. As a large, multi-page folded document, users almost never scan it flat. Instead, they take smartphone photos at extreme angles, causing severe perspective distortion. Furthermore, identifying the critical 11-digit Document Reference Number (essential for verifying if a vehicle is stolen, scrapped, or written off) amidst colored backgrounds and heavy formatting text often causes legacy OCR tools to fail. Learn more about our advanced perspective correction capabilities on our Vehicle Registration OCR product page.

Semantic Parsing & Warp Correction

StructOCR is specifically engineered to handle the chaotic nature of user-uploaded V5C photos. Our visual grounding models automatically deskew and flatten warped images. We utilize semantic Key-Value mapping to reliably locate the VIN and the Document Reference Number, completely bypassing the complex page layout. These specific UK data points are dynamically captured into our flexible `localized.generic.unmapped_fields` object, ensuring no data is left behind. Discover how this fits into broader UK automotive workflows in our Vehicle Registration Solutions guide.

Core Industry Applications

Integration & API Documentation

Easily integrate our full-field OCR API. For full technical details, visit our Developer API Documentation.

import requests
import base64

# 📸 Test for free with your own image upload: https://structocr.com/developers/vehicle-registration-ocr

with open("uk_v5c_logbook.jpg", "rb") as image_file:
    base64_image = base64.b64encode(image_file.read()).decode('utf-8')

url = "https://api.structocr.com/v1/vehicle-registration"
headers = {
    "x-api-key": "YOUR_API_KEY",
    "Content-Type": "application/json"
}
payload = {
    "img": base64_image
}

response = requests.post(url, headers=headers, json=payload)
result = response.json()

if result.get('success'):
    data = result.get('data', {})
    std = data.get('standardized', {})
    print("✅ Standardized VIN:", std.get('vin'))
    print("✅ Standardized Plate:", std.get('plate', {}).get('formatted'))
    
    # UK specific fields are captured in the generic fallback
    loc = data.get('localized', {})
    if 'generic' in loc and loc['generic'].get('unmapped_fields'):
        unmapped = loc['generic']['unmapped_fields']
        print("✅ Document Ref No:", unmapped.get('document_reference_number'))

{
  "success": true,
  "data": {
    "document": {
      "country_code": "GB",
      "document_type": "VEHICLE_REGISTRATION",
      "confidence_score": 0.97
    },
    "standardized": {
      "vin": "SALLSAAJ7EA123456",
      "plate": {
        "number": "AB12CDE",
        "formatted": "AB12 CDE"
      },
      "make_normalized": "Land Rover",
      "year": 2018
    },
    "localized": {
      "generic": {
        "unmapped_fields": {
          "document_reference_number": "1234 5678 901",
          "tax_class": "Diesel Car"
        }
      }
    }
  }
}