Full-Field Japan Vehicle Registration (Shaken-sho (車検証)) OCR

The Challenge: High-Density Kanji and JDM Export Scaling

The Japanese vehicle inspection certificate (Shaken-sho) is critical for the global JDM export market. However, it presents extreme OCR challenges: a mix of dense Kanji, tiny fonts, and complex layout structures. Furthermore, modern digital Shaken-sho IC cards are accompanied by paper prints that suffer from severe anti-counterfeit watermarks, confusing standard OCR engines that struggle with complex Asian typography. Learn more about our robust capabilities on our Vehicle Registration OCR product page.

Advanced Asian Typography & Semantic Extraction

StructOCR is specifically engineered to conquer dense CJK (Chinese, Japanese, Korean) documents. Our engine effortlessly filters out Japanese anti-copy watermarks and isolates high-density Kanji characters. Using advanced semantic Key-Value mapping, it dynamically captures critical export details like Chassis Numbers and exact inspection dates into our `localized.generic.unmapped_fields` object. Discover how this fits into broader JDM export 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("japan-shakensho-full-ocr.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'))
    
    # Japan 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("✅ Chassis Number:", unmapped.get('chassis_number'))
        print("✅ First Registration Date:", unmapped.get('first_registration_date'))

{
  "success": true,
  "data": {
    "document": {
      "country_code": "JP",
      "document_type": "VEHICLE_REGISTRATION",
      "confidence_score": 0.98
    },
    "standardized": {
      "vin": "SAMPLEVIN12345678",
      "plate": {
        "number": "ABC-123",
        "formatted": "ABC 123"
      },
      "make_normalized": "Toyota",
      "year": 2020
    },
    "localized": {
      "generic": {
        "unmapped_fields": {
          "chassis_number": "NCP131-1234567",
          "first_registration_date": "2018-05-15",
          "vehicle_weight_kg": "1040"
        }
      }
    }
  }
}