Extract government IDs to structured JSON

Government-issued IDs hold critical identity data for KYC, onboarding, and compliance. Formats vary by country and state. Sensible turns license, passport, and national ID data into structured JSON for identity verification, fraud detection, and regulatory workflows.

Quick links:

Financial services solutions

API documentation

On-demand product demos

Schedule a demo

Why government IDs challenge extraction tools

Layout differences by state and country, security features, and MRZ data create extraction challenges.

State and Country Variance

Every US state has its own driver's license design, and each revises it periodically. Passports follow ICAO standards but vary by country. Sensible adapts to each jurisdiction's layout while extracting the same core identity fields.

Photo Capture Quality

IDs are typically photographed by users, not flatbed scanned. Glare from holograms, perspective distortion, finger occlusion, and shadows produce images that need correction before extraction begins. Sensible's LLM parsing handles degraded mobile captures that rigid OCR pipelines reject.

Photo and Security Feature Handling

Holograms, watermarks, microprint, and ghost images create visual noise that overlays the text fields. The machine-readable zone (MRZ) on passports encodes identity data with check digits that validate extraction accuracy. Sensible isolates text regions and validates MRZ check digits for a built-in accuracy cross-check.

Fields we extract

Identity fields cover KYC requirements. Configure the schema for your verification workflow.

Identity data

Full name, date of birth, gender, address, document number, issuing authority, issue date, expiration date, nationality

Document-specific

License class/type, restrictions, endorsements, organ donor status (driver's license), MRZ data (passport), visa type

Verification signals

Document expiration status, MRZ check digit validation, photo region coordinates, barcode data (PDF417 for US licenses)


{ /* SenseML: government ID extraction */
  "fields": [
    {
      "method": {
        "id": "queryGroup",
        "queries": [
          {
            // Full name on the ID
            "id": "full_name",
            "description": "full name, name, first name last name"
          },
          {
            // Date of birth
            "id": "date_of_birth",
            "description": "date of birth, DOB, birth date",
            "type": { "id": "date" }
          },
          {
            // Document number (DL number, passport number)
            "id": "document_number",
            "description": "document number, license number, DLN, passport number",
            "type": {
              "id": "custom",
              "pattern": "[A-Z0-9\\- ]{7,}"
            }
          },
          {
            // Expiration date
            "id": "expiration_date",
            "description": "expiration date, expires, EXP",
            "type": { "id": "date" }
          }
          // Additional fields for address, gender, eye color, restrictions, etc.
        ]
      }
    }
  ]
}
Work Permit

Employment Authorization Document (EAD) with category, validity, and USCIS number.

State ID Card

Non-driver state identification card with the same data fields as a driver's license.

US Passport

Machine-readable US passport with MRZ zone, photo, and biographical data.

US Driver's License

State-issued driver's license with photo, address, DOB, and license number.

Supported ID types

Sensible processes driver's licenses, passports, national ID cards, and state IDs from US and international jurisdictions. Hybrid extraction handles the range of document designs and security features.

US documents

Driver's licenses (all 50 states + DC), state ID cards, US passport, US passport card, military ID

International

National passports (ICAO-compliant), national ID cards, residence permits, work permits, refugee travel documents

Trusted by operations and engineering teams at

Common Questions

Answers about ID types, MRZ validation, and jurisdiction support.

Can Sensible validate ID expiration dates?

Yes. Sensible extracts the expiration date and validation rules can flag expired documents automatically. Issue dates and date of birth are also extracted for age verification.

Does Sensible detect photos on government IDs?

Sensible detects photo presence on the ID and extracts all text fields. Photo region coordinates are available for identity verification workflows.

What types of government IDs does Sensible support?

Sensible processes driver's licenses, passports, national ID cards, and state ID cards from the US and many international jurisdictions.

Can Sensible read the MRZ on passports and IDs?

Yes. Sensible extracts Machine Readable Zone (MRZ) data including document number, nationality, date of birth, expiration date, and check digits for validation.

Do you support webhooks?

Yes. Sensible sends extraction results to your webhook endpoint when processing completes. You can also poll the API for status.

Does Sensible support human review?

Yes. Sensible flags extractions with low confidence for human review. You can configure review thresholds and workflows.

What security certifications does Sensible have?

Sensible is SOC 2 Type II certified and HIPAA compliant. Data is encrypted in transit and at rest.

How long is document data retained?

Document data is stored indefinitely by default. Custom retention policies are available and can be configured for same-day deletion if needed.

Is there a free trial?

Yes. Sensible offers a 14-day free trial on the Growth plan. No credit card required to start.

How is pricing structured?

Sensible uses per-document pricing for predictable costs. No token-based billing or usage surprises. Volume discounts are available for higher throughput.

How do I integrate with Sensible?

Sensible provides REST APIs and SDKs for Python and Node.js. Most integrations take a few hours. Webhooks, Zapier, and direct API calls are all supported.

What file formats does Sensible support?

Sensible processes PDFs (native or scanned), Microsoft Word (DOC, DOCX), spreadsheets (XLSX, XLS, CSV), single-page images (JPEG, PNG), multi-page images (TIFF), and email bodies with attachments.

How accurate is the extraction?

Accuracy depends on document quality and configuration. Most production deployments achieve 95%+ accuracy with proper validation rules and confidence signals.

How fast is document processing?

Processing speed depends on document size, page count, OCR requirements, and which extraction methods are used. Simple single-page documents process in seconds. Larger or more complex documents that use LLM-based extraction take longer.

Resources

Documentation Links

Docs: Insurance template quick startDocs: Validation and human reviewDocs: API and delivery options

Related insurance documents

Docs: Insurance template quick startDocs: Validation and human reviewDocs: API and delivery options