Face Match

Documents & Biometrics

Compare a selfie to the photo on an ID document or KYC record.

Confirm the person presenting an ID is the person on it. Send a selfie and a reference photo, from an ID document, Aadhaar eKYC or DigiLocker, and receive a match score with a clear pass or fail against your threshold.

Endpoint

POST https://app.emver.io/api/sandbox/v1/face-match

Authorization: Bearer YOUR_API_KEY

Content-Type: application/json

Accept: application/json

Request parameters

Field	Type	Description
`selfie_image` required	string	Selfie image
`reference_photo_i_d_document_or_k_y_c_record` required	string	Reference photo (ID document or KYC record)

Example request

cURL

curl -X POST https://app.emver.io/api/sandbox/v1/face-match \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -d '{
    "selfie_image": "string",
    "reference_photo_i_d_document_or_k_y_c_record": "string"
}'

import requests

response = requests.post(
    "https://app.emver.io/api/sandbox/v1/face-match",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Accept": "application/json",
    },
    json={
        "selfie_image": "string",
        "reference_photo_i_d_document_or_k_y_c_record": "string"
    },
    timeout=60,
)
response.raise_for_status()
data = response.json()

const response = await fetch("https://app.emver.io/api/sandbox/v1/face-match", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
    "Accept": "application/json",
  },
  body: JSON.stringify({
      "selfie_image": "string",
      "reference_photo_i_d_document_or_k_y_c_record": "string"
  }),
});

const data = await response.json();

$response = Http::withToken('YOUR_API_KEY')
    ->acceptJson()
    ->post('https://app.emver.io/api/sandbox/v1/face-match', {
        "selfie_image": "string",
        "reference_photo_i_d_document_or_k_y_c_record": "string"
    });

$data = $response->json();

Replace YOUR_API_KEY and the placeholder values. Use the switch above to see production URLs.

Response

Structure · 200

{
  "status": INTEGER,
  "message": STRING,
  "data": {
    "match_score": STRING,
    "match_decision_against_threshold": STRING,
    "face_detected_in_each_image": STRING
  }
}

Example · 200

{
  "status": 200,
  "message": "string",
  "data": {
    "match_score": "string",
    "match_decision_against_threshold": "string",
    "face_detected_in_each_image": "string"
  }
}

Error · 4xx / 5xx

{
  "status": INTEGER,
  "message": STRING
}

See Errors & status codes for what each status means and which calls are billed.

About this API

Document checks prove a document is real. Face Match proves the right person is holding it. The API compares two facial images and returns a similarity score, with a decision against the threshold you configure, so onboarding can stop impersonation without a human reviewer.

Pair it with Liveness Detection to be sure the selfie is a live capture and not a photo of a photo.

Consent. Facial images are biometric data. Capture the person's consent before the check; emver stores the consent record and purges images after processing.

Typical uses

Digital account opening. Match the selfie to the eKYC photo.
Gig partner activation. Confirm the rider matches the licence photo.
Remote exams and assessments. Verify the candidate at the start of a session.
High-value transactions. Step-up authentication using a stored reference.

Questions

What threshold should I use?: emver provides recommended thresholds per use case. Higher thresholds reduce false accepts at the cost of more manual reviews.
Can it use the photo from Aadhaar eKYC or DigiLocker?: Yes. The photograph returned by those flows is a strong reference image.