Bangladesh Smart NID OCR Python SDK

Parsing Smart NID Challenges

Extracting data from Bangladeshi Smart NIDs presents unique challenges. Firstly, Bilingual Complexity: the cards contain both Bengali (Bangla) and English text. Standard OCR engines often fail to accurately interpret the complex conjunct characters (যুক্তাক্ষর) of the Bengali script. Secondly, unlike many international IDs, the Smart NID lacks a traditional Machine-Readable Zone (MRZ), relying instead on a dense 2D barcode on the reverse side, making mathematical cross-validation more difficult for generic text-parsing APIs.

Why StructOCR for Bangladesh

Our AI model is pre-trained on hundreds of thousands of Bangladeshi Smart NID samples, enabling advanced national id ocr capabilities. This specialized training ensures over 99% accuracy on both complex Bengali typography and standard English fields. The Python SDK handles all the complexity of image preprocessing, bilingual extraction, and payload decryption, allowing you to deploy seamless kyc automation into your application effortlessly.

Common Use Cases in South Asia

• Digital Onboarding: Verify users for Mobile Financial Services (MFS) like bKash or Nagad by pre-filling NID data instantly.
• Telecom Registration: Automate robust SIM card registration with native Bengali character extraction.
• Pan-South Asia Expansion: Seamlessly process users across the Indian subcontinent. Our unified Python SDK automatically detects and extracts data from neighboring documents, such as the India Aadhaar or Pakistan CNIC, without requiring any custom rules.

Python SDK Integration

Install the SDK via pip: `pip install structocr`. The SDK automatically maps the 10-digit Smart NID fields and gracefully handles the absence of MRZ data.

Prerequisite: Python 3.6+ and `structocr` library installed.

from structocr import StructOCR

# 🔑 Need a key for Bangladesh? Get 200 free credits instantly:
# 👉 https://structocr.com/register
# Initialize with your API Key
client = StructOCR("YOUR_API_KEY_HERE")

def scan_bangladesh_id():
    # Note: Supports JPG, PNG, WebP (Max 4.5MB)
    image_path = "bangladesh_smart_nid_front_back.jpg"

    try:
        print(f"Scanning {image_path}...")
        result = client.scan_national_id(image_path)

        if result.get('success'):
            data = result['data']
            print("✅ Bangladesh Smart NID Extraction Successful!")
            
            # Basic Identity
            print(f"Region:      {data.get('country_code')}")
            print(f"Name (EN):   {data.get('given_names')} {data.get('surname')}")
            print(f"NID Number:  {data.get('document_number')}")
            
            # Demographics
            print(f"DOB:         {data.get('date_of_birth')} ({data.get('sex')})")
            print(f"Address:     {data.get('address')}")
            
            # Note: Smart NID lacks MRZ, payload is strictly null in MRZ fields
            additional = data.get('additional_fields', {})
            if not additional.get('mrz_line_1'):
                print("\nℹ️ Document verified: PDF417 Barcode parsed. No standard MRZ present.")
        else:
            print(f"❌ Extraction Failed: {result.get('error')}")

    except Exception as e:
        print(f"An error occurred: {e}")

if __name__ == "__main__":
    scan_bangladesh_id()

JSON Response Example

The SDK returns a Python dictionary containing the parsed visual data in both English and Bengali. Unused MRZ and LatAm fields are safely returned as null.

{
  "success": true,
  "data": {
    "type": "national_id",
    "country_code": "BGD",
    "nationality": "BANGLADESHI",
    "document_number": "8293481234",
    "card_series": "",
    "personal_number": "8293481234",
    "surname": "AHMED",
    "given_names": "RAHIM",
    "sex": "M",
    "date_of_birth": "1990-05-15",
    "place_of_birth": "DHAKA",
    "address": "বাসা নং ১২, রোড নং ৫, ধানমন্ডি, ঢাকা",
    "date_of_issue": "2020-01-01",
    "date_of_expiry": "2035-01-01",
    "issuing_authority": "Govt. of Bangladesh",
    "additional_fields": {
      "phone_number": null,
      "tramite_number": null,
      "ejemplar": null,
      "mrz_line_1": null,
      "mrz_line_2": null,
      "mrz_line_3": null
    }
  }
}