SOLUTIONS / OKKHI SENTINEL / SEN-12

SEN-12

Face Recognition Access

Recognizes enrolled faces for door access, watchlists, and VIP service — entirely on-premise, no cloud matching.

OKKHI SENTINEL · SURVEILLANCE THAT UNDERSTANDS.
Face Recognition Access — annotated camera view

Matches faces against enrolled lists on your own server — staff for doors, watchlists for alerts, VIPs for service — with every decision logged and nothing ever sent to a cloud API.

Quality gating rejects poor captures instead of guessing, which is what keeps the false-accept rate honest.

TYPICAL DEPLOYMENT
CamerasEntrance IP cameras
ComputeEdge GPU (shared)
MatchReal time
OutputDoor I/O · alerts · audit log
The problem

Access cards get shared and lost, guards can't memorize a watchlist, and cloud face APIs are a privacy and residency non-starter for any serious institution.

Who it's for

Offices, plants, and branches controlling who enters where

The outcome

Access decisions happen hands-free in real time, with a full log of every entry — on your hardware, not a vendor's cloud.

How it works
STEP 1Capture

Entrance cameras watch arrival points continuously.

STEP 2Detect

Faces are found and quality-gated before any matching.

STEP 3Match

On-premise embeddings match against your enrolled lists.

STEP 4Action

Door relays, alerts, or VIP notifications fire — fully logged.

See it in action

Concept demonstration. To show client footage instead, replace media/video/face-recognition-access.mp4 — the page updates automatically.

Where it's used
1Office and plant entry
2Branch VIP recognition
3Watchlist alerting at entrances
4Visitor re-identification across cameras
Related solutions
Request a pilot for SEN-12 Fixed scope · weeks not months · your cameras, your product

Proof beats promises.
See it on your own cameras.

We run a two-week pilot on your footage, with your incidents, measured against your numbers. If the results don't convince you, you keep the full report and owe nothing.

Book a free live demo