Versions Compared

Old Version 2

changes.mady.by.user Alena Kniazeva

Saved on

compared with

New Version Current

changes.mady.by.user Alena Kniazeva

Saved on

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.
Description

The Face

Detection

detector VL generates an event every time a face is captured in the frame.

The 

The Axxon One

 database

 database stores all faces in binary form:

  1. All captured faces are stored as biometric vectors (
see 
  1. see Face search) in
the 
  1. the t_face_vector
 table
  1.  table, and their corresponding capture events are stored in
the 
  1. the t_json_event
 table
  1.  table.
    Note
    titleAttention!

    The default storage depth of face vectors is 24 hours. To specify the storage depth of face vectors, you must add the NGP_FACE_VECTORS_IN_RAM_DEPTH_HOURS system variable (see Creating system variable). The values of the variable are specified in hours.

    For example, if you set NGP_FACE_VECTORS_IN_RAM_DEPTH_HOURS = 1, face vectors are deleted from RAM in one hour. If the value of the NGP_FACE_VECTORS_IN_RAM_DEPTH_HOURS variable isn’t set, the storage depth of face vectors is 24 hours.

  2. All reference faces from the lists (see 
Lists of faces
  1. Faces) are stored in
the 
  1. the t_face_
listed  
  1. listed table.
Note
titleAttention!

When the number of faces in the database increases, the statistical error increases: the more faces in the database, the more often similar faces are recognized when searching in the archive. Accordingly, the degree of similarity when comparing the reference face with the captured face decreases.

This error is relevant if:

The
  1. The Video stream and scene requirements for the Face
Detection
  1. detector VL and its sub-
tools are
  1. detectors are met.
  2. The database contains over a million faces.
An example

Example of the error calculation results:

The mugshot dataset (good quality photo), 12 million faces in the database, and probability of false matching is 0.003%. With these initial data, the researchers obtained an identification error of 0.81%.

 

LicensingTo operate the
detection tool
detector, contact an AxxonSoft manager and get a license file (
see 
see Types of licenses)
Add-ons

For

the 

the Face

Detection

detector VL

 

to work, you must

install VL

install VL Face Recognition Pack and VL SDK Pack (see Installing DetectorPack add-ons).

Note
titleAttention!

You can install only one

 

Face Recognition Pack:

either

VA Face Recognition Pack

/

, TV Face Recognition Pack, or VL Face Recognition Pack. You cannot install

both

several packages in the same system.