Full-Field Thailand Vehicle Registration (Blue Book) OCR

The Challenge: Thai Script Diacritics and Compact Tables

The Thai vehicle registration document (Lem Tabian, often called the Blue Book for cars or Green Book for motorcycles) is an optical challenge. The Thai language inherently lacks word spacing and utilizes complex upper and lower diacritics. In the Blue Book, this text is printed extremely close to rigid table borders, and is frequently accompanied by overlapping official stamps or handwritten notes. Traditional OCR engines that rely on blank space to separate words fail spectacularly here, generating fused strings and gibberish. Learn more about our robust capabilities on our Vehicle Registration OCR product page.

Advanced Thai NLP & Semantic Extraction

StructOCR is specifically engineered to handle the complexities of ASEAN documents. Our engine incorporates deep learning models trained specifically to separate Thai diacritics from overlapping table lines and stamps. It uses advanced semantic Key-Value mapping to intelligently locate both universal fields (VIN, Make) and region-specific parameters. All specialized Thai details are dynamically structured into our `localized.generic.unmapped_fields` object. Discover how this fits into broader compliance 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("thai_blue_book.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 Make:", std.get('make_normalized'))
    
    # Thai specific details 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("✅ Engine Number:", unmapped.get('engine_number'))
        print("✅ Registered Province:", unmapped.get('province'))

{
  "success": true,
  "data": {
    "document": {
      "country_code": "TH",
      "document_type": "VEHICLE_REGISTRATION",
      "confidence_score": 0.96
    },
    "standardized": {
      "vin": "MR0KA3BZ3F1234567",
      "plate": {
        "number": "กท 1234",
        "formatted": "กท 1234"
      },
      "make_normalized": "Toyota",
      "year": 2019
    },
    "localized": {
      "generic": {
        "unmapped_fields": {
          "engine_number": "1NZ-FE123456",
          "province": "Bangkok",
          "vehicle_type": "Sedan"
        }
      }
    }
  }
}