Zero-Retention Passport OCR for Neo-Banks
Accelerate digital account openings without compromising data sovereignty. Process global passports instantly at the edge—where sensitive PII is never written to disk.

The Compliance Liability of Legacy OCR
For Neo-banks and challenger banks scaling globally, fast customer onboarding is a competitive advantage. However, relying on traditional OCR vendors that log, store, or train models on your users' highly sensitive Personally Identifiable Information (PII) creates a massive regulatory liability under frameworks like GDPR and India's DPDP Act. For comprehensive compliance strategies across borders, explore our travel identity verification solutions.
StructOCR: Process-and-Forget Architecture
Designed specifically for modern financial infrastructure, our core Passport OCR engine operates on a strict zero-data-retention philosophy. By deploying entirely on Cloudflare's secure edge nodes, your users' Base64 document streams are processed entirely in-memory and instantly purged. Combined with our pure REST API approach (no black-box SDKs), your Neo-bank retains absolute architectural and legal control over the entire KYC data pipeline.
Live Demo: Passport scanner
No registration required. Upload a file to test the extraction.
Drop files here or click to browse
JPG · PNG · WebP · up to 500 files · max 4.5 MB each
Ready to use this in production? Get 20 free API calls — no credit card needed.
Get 20 Free API Calls →Core FinTech Applications
Digital Account Opening
Reduce Time-to-First-Transaction (TTFT) by automatically extracting and normalizing MRZ and VIZ data in under 1.2 seconds to instantly populate core banking systems.
Cross-Border Onboarding
Seamlessly verify users from 195+ countries. As a global platform, we natively accept USDT/Crypto payments to bypass fiat friction for international SaaS operators. View our API pricing.
Automated AML Screening
Extract deterministic, ISO 8601 formatted names and dates to instantly cross-reference against global sanctions and PEP (Politically Exposed Persons) watchlists.
Crypto-Friendly Banking
Provide a Web3-native onboarding experience with an API that shares your ethos of decentralization and strict data privacy.
Technical Specs
- Zero Data Retention: Built for FinTech compliance. Images and resulting JSON are completely purged from RAM immediately after inference.
- Edge Deployment: Deployed across Cloudflare's global edge network to guarantee ultra-low latency for international users.
- Base64 Native: Stream image data securely without ever exposing sensitive PII to intermediary AWS S3 URLs.
- API-First Architecture: 100% RESTful integration eliminates the security vulnerabilities and version conflicts inherent in mobile SDKs.
Key Features
- Universal MRZ Parsing: Accurately decodes ICAO Document 9303 standard formats with built-in checksum validation to prevent tampering.
- VIZ Fallback: Intelligently extracts data from the Visual Inspection Zone if the MRZ is damaged or obscured.
- Strict Normalization: All dates are returned in reliable ISO 8601 (`YYYY-MM-DD`) format for deterministic backend banking logic.
Integration & AI Prompts
Keep sensitive documents off public cloud storage URLs. Stream Base64 image data directly from your backend to our edge nodes. For complete payload schemas, consult our official Passport OCR Developer Documentation.
import requests
import base64
# 📚 Developer Docs: https://structocr.com/developers/passport-ocr
# Note: StructOCR is an API-first platform. Stream Base64 natively
# from your Neo-bank's backend to maintain a closed-loop data pipeline.
with open("user_passport_kyc.jpg", "rb") as image_file:
base64_image = base64.b64encode(image_file.read()).decode('utf-8')
url = "https://api.structocr.com/v1/passport"
headers = {
"x-api-key": "YOUR_API_KEY",
"Content-Type": "application/json"
}
payload = {
"img": base64_image
}
try:
# Processed securely in RAM at the edge and instantly destroyed
print("Authenticating Neo-Bank User...")
response = requests.post(url, headers=headers, json=payload)
result = response.json()
if result.get('success'):
print("✅ Zero-Retention Extraction Complete!\n")
# Standardized ISO 8601 Data for AML checks
core = result['data']
print(f"Name: {core.get('given_names')} {core.get('surname')}")
print(f"ID No: {core.get('passport_number')} ({core.get('country_code')})")
print(f"DOB: {core.get('date_of_birth')} (ISO 8601)")
print(f"Expiry: {core.get('date_of_expiry')} (ISO 8601)")
else:
print(f"❌ Extraction Failed: {result.get('error')} - {result.get('message')}")
except Exception as e:
print(f"Error: {e}")Standardized JSON Output
Receive deterministic, cleanly structured data ready for immediate insertion into your core banking system.
{
"success": true,
"data": {
"type": "passport",
"country_code": "IND",
"nationality": "INDIAN",
"passport_number": "Z1234567",
"surname": "SHARMA",
"given_names": "RAHUL",
"sex": "M",
"date_of_birth": "1988-07-22",
"place_of_birth": "NEW DELHI",
"date_of_issue": "2021-04-10",
"date_of_expiry": "2031-04-09",
"issuing_authority": "MINISTRY OF EXTERNAL AFFAIRS",
"country_specific": {
"last_page": {
"father_name": "AMIT SHARMA",
"mother_name": "SITA SHARMA",
"spouse_name": "PRIYA SHARMA",
"address": "FLAT 4B, GREENWOOD APARTMENTS, NEW DELHI PIN: 110001, INDIA",
"old_passport_number": "P7654321",
"old_passport_issue_date": "2010-01-05",
"old_passport_issue_place": "DELHI",
"file_no": "DL1076071103622",
"ecr_status": null
}
}
}
}Frequently Asked Questions
How does StructOCR guarantee zero data retention for our banking users?
Our architecture is strictly 'process-and-forget'. When your backend sends a Base64 payload, it is processed entirely in-memory at our Cloudflare edge nodes. The moment the JSON response is dispatched, the memory is purged. We do not write images or extracted PII to any physical disk or database.
Why is an API-first approach better than an SDK for Neo-banks?
Mobile SDKs introduce massive security black-boxes, bloat app sizes, and make cross-platform development (like React Native/Flutter) a nightmare of version conflicts. An API-first approach allows your engineering team to own the entire user experience and data pipeline, simply sending secure HTTP requests to our endpoints.
Can the API process non-standard passports or those with heavy glare?
Yes. While we prioritize the MRZ for structured accuracy, our engine includes a secondary VIZ (Visual Inspection Zone) parsing module that can extract information from the complex visual layouts of passports across 195+ countries, effectively handling real-world mobile capture issues like glare and skew.
Explore More Travel & KYC Solutions
Automated Hotel Check-In Passport Scanner API
Streamline hotel check-ins with our automated passport scanner API. Extract global guest data instantly without SDKs. Upload an image to test our free live demo.
Crypto KYC Passport API (No SDK Required)
Zero-retention Passport OCR API for Web3 and Crypto KYC. Extract global MRZ and VIZ data instantly without SDK bloat. Upload an image to test our free live demo.
DPDP Compliant Indian Passport OCR
DPDP-compliant, zero data retention OCR API for Indian passports. Securely extract back-page PII (Address, Parents' Names) for KYC workflows. File, Base64, and URL supported.
Precise Data Extraction and Seamless
Integration with AI-powered OCR API.
Empower your solutions with automated data extraction by
integrating best-in class StructOCR via API seamlessly.
No credit card required • Full API access included