Fast, Reliable Driver Licence OCR
Extract data from both front and back sides of licenses with advanced PDF417 and QR code decoding, supporting global formats with industry-leading accuracy.
Field Reference
Our OCR engine extracts the following fields from driver licences with high accuracy and confidence scores.
licence_number
Unique identifier for the driver licence
full_name
Full name of the licence holder
dob
Date of birth in ISO format (YYYY-MM-DD)
issue_date
Date when the licence was issued
expiry_date
Date when the licence expires
licence_class
Vehicle classes the holder is permitted to drive
address
Residential address of the licence holder
barcode_payload_json
Decoded data from PDF417/QR barcode
How Accurate Is It?
We have not published a benchmark for driver's licences yet, so we will not put a made-up number here. This is what we have measured, and how errors get caught.
97-99%
Clean Typed Text
Character accuracy on clean typed text in our 2026 OCR benchmark. Printed ID fields are typed text, but glare, wear and angled photos pull it down.
PDF417
Barcode on the Back
US and Canadian licences carry an AAMVA PDF417 barcode that encodes the same details as the front. DocsAPI decodes it alongside the printed fields.
Fields the engine is unsure about are flagged for a reviewer instead of guessed. The best test is your own sample, so bring a few real driver's licences captures to the demo.
Verification Workflow
Our four-step process ensures accurate data extraction and fraud detection for driver licences.
Front Capture
User captures the front of the licence using our SDK with auto-focus and glare detection guidance.
Back Barcode Scan
The back of the licence is scanned to extract the PDF417 or QR barcode data with high precision.
Data Fusion & Validity Check
Front OCR data is cross-referenced with barcode data to ensure consistency and detect tampering.
Fraud Score Output
A comprehensive fraud score is generated based on multiple verification factors and security features.
Time and Checks
What changes when driver's licences are read by DocsAPI instead of typed in by hand
Time
Speed from our 2026 OCR benchmark, including the network round-trip. Capture quality matters more than processing time: a blurry photo costs the user a retake, so guide them to a clean, flat, well-lit shot.
Checks Before the Data Moves On
- PDF417 barcode decoded alongside the printed fields
- Field formats checked before the data moves on
- Low-confidence fields flagged for a reviewer instead of guessed
Fraud catch rates depend on your applicant mix and capture flow, so we would rather test on your samples than quote a number.
Developer Output
Our API returns a comprehensive JSON response with extracted fields, barcode data, and validity scores.
{
"metadata": {
"document_type": "driver_licence",
"issuing_state": "California",
"scan_timestamp": "2023-09-15T14:32:18Z",
"processing_time_ms": 856
},
"fields": {
"licence_number": "F1234567",
"full_name": "DOE, JOHN MICHAEL",
"dob": "1985-06-12",
"issue_date": "2020-03-15",
"expiry_date": "2025-06-12",
"licence_class": "C",
"address": "123 MAIN ST, ANYTOWN CA 90210",
"restrictions": "CORRECTIVE LENSES"
},
"barcode_payload": {
"aamva_version": "08",
"jurisdiction_version": "01",
"inventory_control_number": "12345678901234",
"height_in": "70",
"eye_color": "BRO",
"hair_color": "BRO",
"organ_donor": "Y"
},
"validity": {
"score": 0.97,
"checks_passed": 12,
"checks_failed": 0,
"suspended_status": false
}
}Document Metadata
Includes document type, issuing state/country, and processing metrics for performance tracking.
Barcode Payload
Contains additional data encoded in the PDF417 barcode that may not be visible on the licence face.
Validity Scoring
Provides confidence scores and validation checks to help determine if the licence is authentic and valid.
Frequently Asked Questions
Launch licence OCR today.
Start extracting driver licence data, barcode included. Book a demo and bring a few real licence images to test.
Book a Demo