AttenTech
Operate APIs

Face Recognition (1:N)

Match a face against a watchlist or database in one call.

Get API AccessPrivate beta only
// OVERVIEW

How Face Recognition (1:N) works

Submit a single face and search it against an entire enrolled database — watchlists, staff rosters, or member records — to find the closest match in milliseconds. Built for gate access, blocklist screening, and de-duplication at real-world camera quality.

1:N database search

One face is compared against the full enrolled gallery in a single call, returning the best match instead of requiring a second reference photo.

Confidence-scored matches

Every result ships with a calibrated confidence score so you can tune accept/review/reject thresholds to your own risk tolerance.

Watchlist-aware results

Matches carry the watchlist or database they were found in, so downstream systems know exactly which list triggered the hit.

face
attentechth.com/api/face/search
01// search a face against an enrolled database
02import { Face } from '@attentech/sdk'
03
04const face = new Face({
05 region: 'th-bangkok',
06 pdpa: true,
07})
08
09const result = await face.search({
10 watchlist: 'staff_2026',
11 image: capturedFrame,
12})
13
14if (result.matched) {
15 const { matchId, confidence, watchlist } = result
16 grantAccess(matchId)
17}
// PROCESS

How Face Recognition (1:N) matches a face against your database

A single face is encoded into a numeric signature and compared against every enrolled face in your database in one pass, returning the closest match with its confidence score and the specific watchlist it was found in.

MATCH ID
CONFIDENCE
WATCHLIST
Capture
Encode
Search
Structured Output

Ready to integrate Face Recognition (1:N)?

Get API access in days, or bring us in to run the full workflow for you — sovereignty by design at every step.

Get API AccessPrivate beta only