Full-Field Indonesia Vehicle Registration (STNK) OCR

The Challenge: Two-Part Documents and Heavy Watermarks

The Indonesian vehicle registration (STNK - Surat Tanda Nomor Kendaraan) is uniquely challenging. It is typically printed on a highly watermarked paper and presented alongside a tax document (SKPD) in a two-part plastic sleeve. Users often upload photos where the document is folded, partially obscured, or suffering from severe background pattern interference. Standard OCR engines extract these background patterns as random noise, destroying data accuracy. Learn more about our robust capabilities on our Vehicle Registration OCR product page.

Noise Rejection & Semantic Mapping

StructOCR is specifically engineered to handle complex Southeast Asian documents. Our AI models dynamically reject STNK background security patterns and cleanly extract the foreground text. Our semantic Key-Value mapping intelligently separates the vehicle registration data from the adjacent tax data, capturing localized fields directly into our `localized.generic.unmapped_fields` object. Discover how this fits into broader Indonesian 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("indonesia-stnk-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'))
    
    # Indonesia 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("✅ Nomor Mesin:", unmapped.get('nomor_mesin'))
        print("✅ Nomor Rangka:", unmapped.get('nomor_rangka'))

{
  "success": true,
  "data": {
    "document": {
      "country_code": "ID",
      "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": {
          "nomor_mesin": "JBK1E1234567",
          "nomor_rangka": "MH1JBK111K1234567",
          "warna": "Hitam"
        }
      }
    }
  }
}