Search Live Person
Liveness on one probe image, then 1:N face search (live).
menu_bookAPI reference: Face Search 1:N (Live)expand_more
Official docs: docs.verifik.co/biometrics/search-live-face (liveness on the probe image, then 1:N search).
Base URL https://api.verifik.co. Send a single raw base64 probe in image (no data URL prefix), required os (ANDROID, IOS, or DESKTOP), liveness and match thresholds, and search_mode. This demo uses DESKTOP.
POST /v2/face-recognition/search-live-face
Runs anti-spoofing / liveness first; if it passes, performs similarity search against enrolled faces.
| Header | Value |
|---|---|
| Content-Type | application/json |
| Authorization | Bearer <token> |
| Param | Req | Description |
|---|---|---|
| image | Yes | Single base64 probe image |
| os | Yes | ANDROID, IOS, or DESKTOP |
| liveness_min_score | Yes | Liveness threshold (0.5–1.0) |
| min_score | Yes | Match threshold (0.5–1.0 per docs) |
| search_mode | Yes | FAST or ACCURATE |
| collection_id | No | Scope search to one collection |
await fetch("https://api.verifik.co/v2/face-recognition/search-live-face", {
method: "POST",
headers: {
"Content-Type": "application/json",
Authorization: `Bearer ${accessToken}`,
},
body: JSON.stringify({
image: "<base64>",
os: "DESKTOP",
liveness_min_score: 0.65,
min_score: 0.75,
search_mode: "FAST",
collection_id: "<optionalCollectionMongoId>",
}),
});- This demo uses
searchLivePersonfrom@humanauthn/api-clientwith your session token. - Failures below the liveness threshold may return an error response (see API docs for error shapes).
Related documentation
Official guides on docs.verifik.co
The Person Object
Fields and structure of a face recognition person record.
List All Persons
Persons for your client, with optional filters.
Retrieve a Person
A single person by id.
Update a Person
Profile, images, collections, and more.
Delete a Person
Remove a person record by id.
Face Search 1:N (Live)
Liveness on the probe image, then 1:N search for matches.