Skip to content
Amani logo

Face Match 1:1

Match a selfie to a document in milliseconds.

The document is real and the person is live - but are they the same person? Face Match 1:1 compares the selfie to the document portrait (or NFC chip photo) and returns a calibrated similarity decision in milliseconds.

Capabilities

What Face Match 1:1 gives you.

Selfie ↔ document binding

The core biometric link that turns a document check into an identity verification.

Accuracy across demographics

Models benchmarked for consistent false-match rates across age, gender and skin tone.

Ages gracefully

Robust matching against document photos taken up to a decade earlier.

Chip-photo support

Uses the high-resolution NFC chip portrait as reference when available for maximum accuracy.

Tunable thresholds

Set match strictness per journey and risk tier; every score is returned for your records.

Pairs with Liveness

Liveness proves presence; Face Match proves identity - run together in one capture.

From session to signed result.

Four steps - the same integration pattern as every Amani module.

01

Create a session

One API call (or a Studio journey) starts a verification session for this module.

02

User completes the flow

Your customer is guided through capture in your branded UI - web or mobile.

03

Checks run in real time

Face Match 1:1 executes alongside any other modules in the journey.

04

You receive a signed result

A webhook delivers the decision, scores and evidence to your backend.

For developers

Integrate Face Match 1:1.

Authenticate, create a profile, generate a verification URL - then let Amani handle the rest. Or describe what you want to your AI coding agent and let Amani Skills wire it up from the live docs.

Available on

BioMatch SDK (Android, iOS)Web SDKKYC SDK

verify.sh

# 1 · Authenticate (server-side only)
curl -X POST 'https://ae.amani.ai/api/v2/user/login/' \
  --form 'username="you@company.com"' \
  --form 'password="••••••••"'

# 2 · Create the customer profile
curl -X POST 'https://ae.amani.ai/api/v2/profile' \
  -H 'Authorization: Bearer $ACCESS_TOKEN' \
  --form 'id_card_number="784199012345678"' \
  --form 'name="Layla Haddad"'

# 3 · Generate the verification URL
curl -X POST 'https://ae.amani.ai/api/v2/profile/url' \
  -H 'Authorization: Bearer $ACCESS_TOKEN' \
  -H 'Content-Type: application/json' \
  --data '{
    "profile": PROFILE_ID,
    "web_sdk_url": "https://verify.amani.ai",
    "language": "en",
    "return_url": "https://yourapp.com/verified"
  }'

# Face Match 1:1 runs inside this session - configure it in Amani Studio.

Face Match 1:1 - common questions

How accurate is the matching?

Thresholds are tuned so genuine users pass first time while false matches stay rare, and every comparison returns a score you can set your own accept, review and reject bands against. We are happy to benchmark on a sample of your own traffic.

What reference images can be used?

The document portrait, the NFC chip photo, or a previously enrolled selfie - whichever your flow provides.

What if the match is borderline?

Borderline scores route to your review queue with both images side-by-side; thresholds for auto-pass, review and fail are yours to set.

Related modules

Add Face Match 1:1 to your flow

Switch it on in Amani Studio, or call it directly from the API.