...
A developer reviewing the result of a face search

Face Recognition API: Search a Face Across Your Own Lists

A REST API for the face engine itself: build person lists, enrol faces into them, and search a new face across a whole list with one call. Matches come back above the threshold you set, with the records you stored.

Read the API DocsAPI docs
  • 1:N search across your own lists 1:N search
  • TOP-24, NIST FRVT 1:1 Verification NIST FRVT TOP-24
  • Person lists, faces and sources over REST Lists over REST
  • Cloud or on-premises Cloud or on-prem

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

Independently tested and certified

ISO register global certification markASIB certification markQA Compliance Assessment certification mark
  • ISO/IEC 27001:2022
  • GDPR
  • iBeta ready
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
What it answers

What the Face Recognition API Answers

Questions about a face, answered from your own lists.

Every answer below comes from comparing one face with something you already hold: a list you built, a person already in it, or the photo in a document. The engine returns candidates and a score; the decision stays in your code.

Is this face already in my records?

A new face is searched across a person list — your customers, your staff, or faces you have blocked — and every match above your threshold comes back with the person record you stored.

1:N search

Do these two faces belong to one person?

A single comparison between two images: a selfie and the photo in a document, or a selfie and the face you saved at onboarding.

1:1 comparison

Is this face on a list I blocked?

Keep a blacklist as a person list of its own and search against it before the account is opened. A match comes back with the record you stored for that person.

Blacklist

How close is the match?

Every candidate carries a similarity score, and the search applies the threshold you pass with it. Stricter for a payout, looser for a low-risk step — the engine returns the candidates, your rules make the call.

Threshold

Is anyone else in the frame?

A second face in the frame is detected, so a customer cannot be prompted or stood in for by someone standing next to them.

Foreign face

Is the face real and present?

Liveness belongs to the session, not to the search: a face arrives in your list from a session where liveness has already confirmed a real person in front of the camera.

In the session
How it works

From a List to a Match in Four Calls

Each step below is one POST, under the name the method has in our public reference.

Every method on this page is in the API reference under the same name.

  1. Create a person list

    POST /person/list/create gives you a list to hold the people your system should recognize — your customers, your staff, or faces you have blocked.

  2. Add people from photos

    POST /person/create uploads the photo into the list with the business fields you keep. The response says how many faces it found and which records in the list already matched.

  3. Search the list at the next check

    Turn the person-list search on in your verification scenario, and every new selfie is checked against the lists you name. A match on a blacklist blocks the session.

  4. Read the matches and act

    The matches come back with the records you stored, above the threshold you set. Your rules decide whether the session is approved, flagged or blocked.

Developers

Add a Face in One Call

One POST uploads the photo, creates the record in your list, and tells you which people in that list it already matched.

terminalREST API
curl -X POST $NV_API_URL/person/create \  -H "Authorization: Bearer $JWT" \  -F "list_id=$LIST" -F "fields=$NAME" \  -F "image=@selfie.jpg"Example only — see the docs for the full request body.
errors{ "status": …, "message": "…", "details": … }
Trust and data

Where Your Data Lives and Stays

Run the checks in our cloud, or inside your own perimeter.

ISO/IEC 27001:2022Certified security system
  • JWT for every call
  • Permanent access tokens
  • On-premises deployment
  • You set image retention
API

What the Reference Covers for Faces

Five groups of methods, named as they are in the docs.

Names below are the ones in our public reference, so you can find each method without guessing what we called it on a landing page.

Person lists

Create a list, read all the lists you hold, update one or delete it. A list is the set of people your system should recognize.

4 methods

Persons and faces

Create a person record, read it, list the people in a list, update the record, delete one or several, and attach face images with a fusion vector.

6 methods

Vector search

One method compares a face vector you already hold against the lists you name, with the threshold you pass, the result format you choose, and the person data returned when you ask for it.

1 method

Data sources

Create sources and source groups, list them, update and delete. Faces arrive from a source, and groups keep lists manageable as they grow.

8 methods

Access and tokens

Authorize a user for a temporary JWT, create a permanent token, list the tokens you hold, update one or delete it.

5 methods
API

Three Ways to Use the Face Engine

The same engine runs inside a KYC session, behind direct REST calls, or entirely inside your own perimeter.

View documentation

Choose Your Integration Path

Inside a KYC session

Turn the selfie and the person-list search on in your scenario, and the face steps run with the document checks. No separate integration.

Direct REST calls

Call the person, vector and source methods yourself when the face check is not part of an onboarding — a returning user, a staff check, a list you maintain.

On-premises

Run the engine inside your own perimeter when the images may not leave it. Deployment is agreed for your case.

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

Faces, Vectors and Who Can Reach Them

Certified information security

The platform runs under an information security management system certified to ISO/IEC 27001:2022.

Read the security policy
ISO register global certification mark ASIB certification mark QA Compliance Assessment certification mark

Every call carries a token

A login returns a temporary JWT, and permanent access tokens are issued for server-to-server calls. Tokens are created, updated and deleted through the API, so access can be withdrawn without touching your code.

You decide where the faces are kept and for how long

Run the engine in our cloud or inside your own perimeter, and set how long images are kept. Person lists stay yours: what is in them, where the photos came from, and who changed what is recorded in the platform.

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
Pricing

Face Recognition API Pricing

There is no separate licence for the face API. You pay per completed check, in the package that includes the face steps.

Basic package

From $0.44 per check

The Basic package adds the selfie, the face comparison and the person-list search to the document check. Build your own set in the price calculator.

Calculate your price

Pay as you go

No subscription and no separate contract for the face API — you pay per completed check.

See Pricing

Free trial

A 14-day trial on your real traffic with full API access and sandbox access from day one.

Volume and enterprise

Custom terms for high volumes, on-premises deployment and an SLA.

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

Not sure which product fits? Tell us about your flow

Tell us the size of the base you want to search and how the faces reach you, and we will confirm what fits your case.

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

Face Recognition API FAQ

What developers ask before they build against the face engine. The full reference is in the documentation, and we link to it.

Didn’t find your answer?

Verification is a 1:1 comparison — is this selfie the person in this document? Recognition is a 1:N search — is this face anywhere in the list? The same engine does both, and this page is about the search.

The 1:1 side has its own page: face verification covers selfie-to-ID matching and what the NIST result means.

POST a photo to /person/create with the list and the business fields you keep. The response tells you how many faces were found in the image and which records in that list already matched.

Yes. The search method takes a face vector, the lists to search in and the threshold to apply, so you can search without uploading an image. The person records come back with each match when you ask for them.

We do not publish a limit. Tell us the size of the base you are planning and we will confirm it for your case.

Yes. Person lists, the faces in them and the search method are separate from the KYC session, so you can enrol faces you already hold and search against them. Liveness, which proves a real person is in front of the camera, runs in a session.

We ship a Web SDK widget for the browser and a REST API for your backend. When the images may not leave your perimeter, the platform is deployed on-premises — tell us your case and we will confirm what fits.

There is no separate API licence. You pay per completed check, from $0.44 in the Basic package. Build your own set on the pricing page.

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

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