Versions Compared

Old Version 3

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
Note
titleAttention!

Starting with with DetectorPack 3 3.11.1, the the Face Detection detector TV is  is no longer supported. We replaced it with the the Face Detection detector VA. You cannot use the the Face Detection TV and the Face Detection VA at detector TV and the Face detector VA at the same time (see  Manual for switching from the Face Detection detector TV to Face Detection detector VA).

The The Face Detection detector TV generates an event every  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 (
    2. see 
  2. see Face search) in
    3. the 
  3. the t_face_vector
    4.  table
  4.  table, and their corresponding capture events are stored in
    5. the 
  5. the t_json_event
    6.  table
  6.  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 Appendix 9. 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.

  7. All reference faces from the lists (see 
    8. Lists of faces
  8. Faces) are stored in
    9. the 
  9. the t_face_
    10. listed 
  10. listed table
    11. .
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:

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

Example of 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 0.76%.

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

For the Face Detection TV the Face detector TV to work, you must install TV Face Recognition Pack add-on on (seesee Installing DetectorPack add-ons).

Note
titleAttention!
  • You can install only
    • one Face
  • one Face Recognition Pack:
    • eitherTV
  • VA Face Recognition Pack, 
    • or 
  • VL Face Recognition Pack, or TV Face Recognition Pack. You cannot install
    • both
  • several packages in the same system.
  • TV Face Recognition Pack is guaranteed to work on Linux Debian 11
    • and Ubuntu
  • and Ubuntu 20.
    •  
  • TV Face Recognition
    • Packs isn
  • Packs isn'
    • t guaranteed
  • t guaranteed to work
    • on Linux
  • on Linux Debian 9/10, Ubuntu 18 and Ubuntu 19 (see Operating system requirements).