Automated Document Discriminator (DD) Extraction

Why is the Document Discriminator (DD) Hard to Extract?

The Document Discriminator (DD)—also known as the audit number or item number—is a critical security feature on modern US driver's licenses. Issuing states use this unique string to track the physical card's manufacturing and issuance, making it essential for detecting counterfeit IDs. However, extracting it is notoriously difficult for standard OCR tools. The DD is often printed in a microscopic font, placed vertically on the edges, or buried within complex holographic backgrounds that vary wildly across all 50 states. To see how our models bypass these optical challenges to isolate secure fields, explore our core driver license OCR infrastructure.

Precision Extraction on the Edge

StructOCR solves the DD extraction problem by utilizing layout-aware AI models that understand the specific topography of each state's ID. Delivered as a pure REST API, you are not forced to install bulky, performance-draining SDKs into your frontend applications. Our core infrastructure is deployed on Cloudflare's global edge network, ensuring ultra-low latency for every request. The API offers maximum flexibility for developers, natively supporting direct file uploads, Base64-encoded strings, and image URLs.

Critical Use Cases for DD Extraction

Integration & AI Prompts

Integrating DD extraction takes minutes. Our endpoint automatically sanitizes Base64 payloads (removing illegal whitespaces) and processes files up to 4.5MB. For complete payload parameters, check our developer documentation. You can also pass the prompt below to your AI coding assistant.

import requests
import base64

# 1. Prepare Base64 Image of the US Driver's License
with open("us_id_sample.jpg", "rb") as image_file:
    base64_image = base64.b64encode(image_file.read()).decode('utf-8')

url = "https://api.structocr.com/v1/driver-license"
headers = {
    "x-api-key": "YOUR_API_KEY",
    "Content-Type": "application/json"
}

# Send pure Base64 string directly to the API
payload = {
    "img": base64_image 
}

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

if result.get('success'):
    data = result['data']
    print(f"✅ State: {data['region']}")
    print(f"✅ License Number: {data['document_number']}")
    print(f"✅ Document Discriminator (DD): {data['extra_details']['card_security_number']}")

{
  "success": true,
  "data": {
    "type": "drivers_license",
    "country_code": "USA",
    "region": "TX",
    "document_number": "12345678",
    "personal_number": null,
    "surname": "DOE",
    "given_names": "JONATHAN MICHAEL",
    "sex": "M",
    "date_of_birth": "1988-07-22",
    "place_of_birth": null,
    "date_of_issue": "2022-03-14",
    "date_of_expiry": "2028-07-22",
    "date_of_first_issue": null,
    "issuing_authority": "Texas DPS",
    "address": "456 LONGHORN DR, AUSTIN, TX 78701",
    "vehicle_class": "C",
    "extra_details": {
      "card_security_number": "0001234567890123"
    }
  }
}