Face recognition
Identify people across every camera, against watchlists of any size.
Match faces from live video or photos against your database, with 1:1 verification and 1:N identification across 1.5 billion faces in 0.3 seconds.
What it does.
Every face in every frame is detected, turned into a template and matched against your enrolled database. Put persons of interest on a watchlist and get an alert the moment one appears on any camera. Search back through recorded events with a photo to see where and when someone was seen.
- 0.3 s
- to search 1.5 billion facial images
- 24×7
- across an unlimited number of video streams
- 1:N identification
- Find one face in a database of millions, in milliseconds.
- 1:1 verification
- Confirm a person is who they say they are, for access control and eKYC.
- Watchlist alerts
- Get notified when a person of interest appears on any camera, day or night.
- Search by photo
- Upload a photo and see every past sighting, with the time and the camera.
- Built for real CCTV
- Works with the pose, lighting and blur of ordinary security cameras, not just studio photos.
How it works.
- 01
Ingest
Live RTSP cameras or recorded footage, from the cameras you already have.
- 02
Detect
Every frame is analysed for the people, vehicles and objects this product looks for.
- 03
Match
Detections are compared with your watchlists, rules and zones.
- 04
Alert
Matches reach your team with the frame, the camera and the time.
On-premises or cloudInstalled on your systems, in the cloud, or both.
REST APIsIntegrate with your video analytics application and third-party software.
Your camerasWe size the hardware and recommend cameras. The cameras stay yours.
Powers these analytics.
Face recognition is part of the recognition engine the rest of the platform runs on.