Live Face Matching provides real-time facial image matching for video surveillance systems deployed in public and commercial buildings, hospitals, banks, railways, cruise lines, airports, and many other places where continuous proactive threat detection is essential.

LFM client sequentially reports subjects registered in the image database:

  • Large images of matching faces.
  • Stored subject images.
  • Alarm notification.
  • Date and time of match, LFM threshold, confidence rating, camera of match.

Live Face matching system includes many phases: face detection; capturing video stream (ZNS Software); feature extraction, and face matching.

ZNS Software

Captures video streams and takes images/video sequences as an input and locates face areas within these images. This is done by separating face areas from non-face background regions

Facial Feature Extraction

Locates important features, including eye, mouth, nose and eyebrow positions, within a detected face.

Face Matching and Identification

Is done by LFM software that matches a facial image that is extracted from the live video of surveillance cameras.

The following products are a part of the tested configuration.


Live Face Matching software (LFM) is a product that can match a facial image that is extracted from the live video of surveillance cameras immediately to the facial image of the target person’s database that has been previously registered. In case the facial similarity rate is greater than or equal to the fixed value, LFM can report an alert to the operator (that is, security personnel monitoring the system). LFM consists of the identify server software running on a identify server with Linux, and the client operation software running on a client PC with Microsoft® Windows®.

Identify server software can input live video of a maximum of 4 cameras, and it can match at a high-speed maximum of 60 faces per second. LFM also provides a movie file identify function, that can match any of the uploaded video files to the server.

Enhanced the security level without the operation change.

  • Suitable to combine with cameras shooting low traffic street, gate, entrance etc.
  • Identified persons can be displayed as a pop-up on the map in real-time.
  • Recognition with no need of specific motion of person.