...
Document OCR: a specimen passport is read and its MRZ and data page fields are returned as JSON

Document OCR for Passports, ID Cards and Driver’s Licenses

Turn a photo of an identity document into structured data. Our document OCR detects the document type and country, reads every field — including the passport MRZ and handwritten entries — and returns it as JSON through one API.

See Supported DocumentsSupported Documents
  • 16,000+ document types 16,000+ document types
  • 195+ countries and territories 195+ countries and territories
  • MRZ checksum verification MRZ checksum verification
  • 90+ languages 90+ languages

12,000 free verifications when you first connect

Every company connecting to NeuroVision for the first time gets 12,000 free verifications for 12 months. Available from December 1, 2026.

Learn more

Banks, fintechs and public services read documents from 195+ countries and territories with NeuroVision.

  • REST API
  • Web SDK
  • JSON output
Global coverage

16,000+ document types
from 195+ countries and territories

Customers verify with the ID they actually carry — in 90+ languages, including handwritten fields and MRZ.

16,000+

document types


Passport ID card Driver's licence Residence permit Visa Work permit Voter card Tax ID eID Biometric passport Military ID Health card National ID Travel document Refugee ID Social security card
195+

countries and territories


Kazakhstan UAE Germany United Kingdom Singapore India Brazil Nigeria Philippines Vietnam Türkiye Mexico Uzbekistan Egypt Indonesia France Spain Italy Poland Kenya Saudi Arabia Japan South Korea Australia United States Canada Thailand Malaysia South Africa
Documents

Document Data Extraction for 16,000+ ID Types

Passports

Ordinary, diplomatic and service passports and ePassports — the data page and the machine-readable zone.

National ID cards

Front and back of national ID cards, including the IDs of Singapore, Malaysia, Indonesia, the Philippines, Vietnam and Thailand.

Driver’s licenses

Driver’s licenses from around the world, with each side read as a separate document.

Residence permits and visas

Residence permits, visas and other documents for foreign customers and employees.

Document OCR starts with knowing what you are reading.

We recognize 16,000+ identity document types from 195+ countries and territories, so the system knows which fields to expect on each one.

How it works

How Document OCR Works

A phone camera instead of a passport scanner — and structured data in under a second.

  1. 1. Capture or upload

    The customer photographs the document in our Web SDK, or your backend sends the image through the API. Guided capture asks them to fix glare, blur and cropped edges before the photo is taken.

  2. 2. Document type and country detected

    No need to tell the system what it is looking at: the document type, version and issuing country are detected automatically.

  3. 3. Fields read and checked

    Every field is read with our OCR engine, MRZ check digits are recalculated, and dates and numbers are checked for consistency.

  4. 4. Structured data returned

    You get the document name, country code and every field with its value and a confidence level — as JSON, in the API response or in the dashboard.

Passports

Passport OCR: MRZ and Data Page

  • MRZ reading and checksum verification

    The two lines of the machine-readable zone are read and every check digit is recalculated, so a mistyped or altered passport number, date of birth or expiry date shows up at once.

    Passport number Date of birth Expiry date
  • Data page fields

    Name, nationality, date of birth, sex, document number, dates of issue and expiry and issuing authority are read from the visual zone of the data page.

    Name Nationality Date of birth Document number Issuing authority
  • Older passports without an MRZ

    Older passports and travel documents without a machine-readable zone are still recognized and read field by field.

    Older passports Travel documents
ID cards

ID Card OCR: Every Field With a Confidence Score

Front and back sides

Both sides of an ID card are read and combined in one session, so you get the full record — not half of it.

Printed and handwritten text

Our own OCR engine reads printed and handwritten fields, so older documents and handwritten entries do not need manual typing.

Confidence for every field

Each field comes back with a confidence level. Low-confidence fields are flagged, so you can ask for a better photo or send the document to manual review instead of trusting a guess.

Southeast Asia

OCR for Southeast Asian ID Documents

Read the documents your customers in Southeast Asia actually carry. National ID cards, driver’s licenses and passports from all six markets are on our list of supported documents. Last reviewed: October 2026.

Singapore

National ID cards in our list
ID cards #1–#3, front and back (incl. back sides for Dependant’s Pass and Visit Pass)
Other documents in our list
Driver’s licenses, passports and ePassports (2006, 2017)
National ID cards in our list
ID cards (2000, 2001, 2012), front and back
Other documents in our list
Driver’s licenses (1989, 2013), passports and ePassports (2006–2017)
National ID cards in our list
ID cards (2004, 2011), front and back
Other documents in our list
Driver’s licenses (2004, 2019, 2022), passports, residence permits
National ID cards in our list
ID cards (2018, 2020), UMID cards (2010, 2016, 2021)
Other documents in our list
Driver’s licenses (2000, 2017, 2022), postal and professional IDs, passports
National ID cards in our list
ID cards (2012, 2016, 2021), front and back
Other documents in our list
Driver’s licenses (1993, 2008), passports (2005–2023)
National ID cards in our list
ID cards (2004–2011), foreigners’ ID card (2016)
Other documents in our list
Driver’s licenses, motorcycle licenses, passports and ePassports
Checks

OCR You Can Trust: Checks on Every Document

Checksums and logical consistency

MRZ check digits, impossible dates and numbers that contradict each other are flagged — so you know when the data itself is wrong, not just hard to read.

When On every document
Checks
  • MRZ check digits
  • Impossible dates
  • Numbers that contradict each other
API

Document OCR API

Send one image or several — document sides and a selfie — in a single request and get the recognized document and its fields back in JSON.

View API Documentation

Choose Your Integration Path

One request, sync or async

POST /kyc/process accepts an array of images, recognizes each document and returns the OCR fields. Run it synchronously for an instant answer or asynchronously for large batches, and fetch the result later by session ID.

Web SDK for guided capture

Let our widget take the photo: it checks framing and glare on the customer’s phone and sends a clean image for OCR.

Mobile SDKiOS & Android

Native SDKs that bring document scanning and selfie capture directly into your mobile app.

Every integration includes:

  • step-by-step implementation guides
  • sandbox with test data
  • dedicated technical support
  • an account manager who speaks both business and tech
  • regular check-ins

Back-office included

  • scenario builder
  • stop-lists
  • manual review and analytics
Use cases

Where Teams Use Document OCR

Onboarding forms that fill themselves

Customers photograph their ID instead of typing their name, date of birth and document number — fewer typos, faster sign-up.

Banks, e-wallets and lending

Pre-fill account and loan applications with data read from the ID, then run full verification on the same image.

Telecom and SIM registration

Capture subscriber data from the ID at the counter or in the app for SIM registration records.

Government and public services

Read citizens’ documents for digital public services, with on-premises deployment where data must stay in the country.

HR and remote hiring

Read candidates’ IDs during remote onboarding instead of retyping them from scans.

Why us

Why teams choose NeuroVision Global Systems

Accuracy you can audit

Independently tested face matching, a confidence score on every result.

Accuracy you can audit

The face algorithm was tested by NIST and placed TOP-24, NIST FRVT 1:1 Verification. Every document and face result comes with a confidence score.

TOP-24NIST FRVT 1:1 Verification
0.1 sper face comparison

Live in under an hour

REST API, Web SDK, iOS and Android SDK, WebView; sandbox first.

Live in under an hour

Under an hour for REST API or Web SDK with sandbox keys; production in one business day. A 14-day trial on your real traffic comes with full support.

< 1 hto integrate with sandbox keys
14 daystrial with full API access

Global coverage

195+ countries and territories, 16,000+ document types, 90+ languages.

Global coverage

Customers verify with the ID they actually carry: 16,000+ document types from 195+ countries and territories, including handwritten fields and MRZ.

16,000+document types
90+languages

Anti-fraud built on real attacks

40+ document checks, 1:N face search, blacklist screening, 30 more layers.

Anti-fraud built on real attacks

Deepfake-resistant liveness, 1:N deduplication and blacklist screening on top of document checks — one person, one account.

40+document checks
0.01%residual fraud risk

Privacy by design

ISO/IEC 27001:2022, GDPR-ready; on-premises, cloud or hybrid.

Privacy by design

Run it in our cloud, in your data centres or hybrid — templates and personal data never leave your jurisdiction.

27001:2022ISO/IEC certified
GDPRready

In-house engines only

OCR, face, liveness and anti-fraud are ours.

In-house engines only

One vendor covers KYC, KYB, AML and KYT on one API — one SLA, no third-party licences.

20 yearsof computer-vision engineering
1 SLAfor every check
Why NeuroVision

Why Choose NeuroVision Document OCR Software

Built for identity documents

Document type, country and field layout are known in advance for 16,000+ documents.

MRZ and checksums included

Passport data is validated, not just read.

Southeast Asian IDs

National IDs, licenses and passports from all six markets on our supported list.

Our own OCR engine

No third-party OCR licenses: one vendor, one SLA.

JSON in under a second

Structured fields with confidence levels, ready for your systems.

Cloud or on-premises

Run OCR in our cloud or in your own infrastructure.

Security

Security and Data Retention

Images and extracted data

Images and extracted data are encrypted in transit and at rest.

Original images

Original images are kept for three months by default and then according to your plan, and you decide how long data stays with us.

Information security management system

Our information security management system is certified to ISO/IEC 27001:2022.

Information security policy
ISO register global certification mark
Products

Our AI-Powered Identity Solutions

Everything you need to verify, authenticate, and protect your customers — all in one powerful platform.

A real person with a real document — verified in seconds. Document capture, face match, liveness, anti-fraud and AML.

Learn more

Screen every customer against sanctions, PEP and watchlists, including self-exclusion lists — inside the same verification flow.

Learn more

Verify the business behind the account: company registry data and ultimate beneficial owners (UBO), checked before onboarding.

Learn more

Transaction monitoring in real time: suspicious transfers are flagged for review, on the same API as KYC and AML.

Learn more

A real, present person — deepfake-resistant. Authenticate returning customers by face instead of passwords.

Learn more

Payments confirmed with a face or an ID document — the identity your customer already verified, at checkout.

Learn more
Contacts

Try Document OCR Free

Send us a few sample documents — specimens or test IDs — and see the extracted fields and JSON for yourself in the sandbox.

Prefer to reach out directly?
Name *
Please enter a valid name
Company
E-mail *
Please enter a valid e-mail
Phone
Please enter a valid phone
Your Message (optional)
Please accept the privacy policy
FAQ

Document OCR FAQ

Didn’t find your answer?

Document OCR (optical character recognition) reads the text on an identity document and turns it into structured data — name, date of birth, document number and other fields — so nobody has to type it in.

16,000+ document types from 195+ countries and territories: passports, national ID cards, driver’s licenses, residence permits and visas. See the full list →

Yes. We read the machine-readable zone and recalculate its check digits, so altered or misread numbers and dates are flagged.

Yes, our OCR reads both printed and handwritten text.

Yes. ID cards, driver’s licenses and passports from Singapore, Malaysia, Indonesia, the Philippines, Vietnam and Thailand are on our list of supported documents.

JPEG and PNG. The document should take up at least 200 pixels on its longer side, be in color, in focus and fully in the frame.

On our production servers a document is recognized and its fields extracted in about half a second.

Document OCR reads the data from a document. Document verification also checks that the document is genuine — screen photos, photocopies, edited images and forged data. You can run both on the same image. See document verification →

Send images to our REST API or use the Web SDK to capture them in the browser. Start in the sandbox with test data, then switch to production. See the API documentation →

All-in-One Face Recognition Platform
for Instant KYC Verification

Streamline onboarding, prevent fraud, and ensure KYC/AML compliance