Versions Compared

Old Version 3

changes.mady.by.user Evgeniya Kononova

Saved on

compared with

New Version Current

changes.mady.by.user Evgeniya Kononova

Saved on

Key

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

Configure the basic settings of the Face Detection module as  module as follows:

  1. Go to
    2. the 
  2. the Basic settings
    3.  tab
  3.  tab on the settings panel of
    4. the 
  4. the Face Detection
    5.  object
  5.  object.
    Image Modified

  6. There are several variations of the face detection operation depending on the setting of the external capture and Face

    7. Recognition Server

  7. recognition server (1):

    1. External capture is NOT selected, and the detection is NOT added to any channel of the Face
    8. Recognition Server channels
    1. recognition server. In this case,
    9. only capturing of
    1. faces
    10. detected
    1. are captured by Axxon PSIM face capturing
    11. is performed
    1. , and
    12. generation of vectors is not performed
    1. vectors aren't generated. This option
    13. is not for
    1. isn't used in Face PSIM.
    2. External capture is NOT selected, but the detection is added to
    14. any
    1. some channel of
    15. the
    1. the Face
    16. Recognition Server channels
    1. recognition server. In this case,
    17. capturing and saving of
    1. the photos of
    18. faces detected by
    1. captured faces are captured and saved by Axxon PSIM face capturing,
    19. generation of
    1. the vectors are generated and
    20. recording them
    1. saved to the database
    21. are performed. This option does not allow face recognition (while
    1. . Face recognition, search and visitor counting are available
    22. )
    1. with this option.
    2. External capture is selected, but the detection is NOT added to any channel of the Face
    23. Recognition Server channels
    1. recognition server. In this case, the photos of faces captured by the face recognition modules (see Structure of the Face PSIM software package)
    24. ,
    1. are captured and saved, and the vectors are generated, but the vectors
    25. are not saved in
    1. aren't saved to the database. This option is only suitable for use in scripts.

    2. External capture is selected, and the detection is added to any channel of the Face

    26. Recognition Server channels

    1. recognition server. In this case,

    27.  the

    1. the photos of faces captured by the face recognition modules (

    28. see

    1. see Structure of the Face PSIM software package)

    29. ,

    1. are captured and saved, and the vectors are generated and

    30. recorded

    1. saved to the database.

    31. The

  31. We recommend using the external capture

    32. is recommended for use

  32. . From

    33. the

  33. the External capture drop-down list, select the Face

    34. Recognition Server with the help of which the face capturing

  34. recognition server that will capture faces with the subsequent generation of a vector (if

    35. the

  35. the Create FIR in detection unit checkbox is set on the settings panel of the corresponding Face

    36. Recognition Server object – see

  36. recognition server object—see Configuring the Face

    37. Recognition Server

  37. recognition server object) and saving of photos

    38. will be performed. Info
    titleNote
    Proper configuring of the face recognition server selected as external capture is performed with the help of the Cfgedit.exe utility (detailed information about this utility see in the Cfgedit

  38. .

    39. exe utility for configuring the Cognitec face recognizer section).

  40. The Maximum performance mode is enabled by default (2). This mode allows improving the quality of face capture and recognition by using all available processor cores and increasing the RAM consumption.
    41. When
  41. If you disable this mode
    42. is disabled
  42. , the memory consumption
    43. will decrease
  43. decreases, but faces can be missed
    44. at capturing
  44. when capturing.
    Info
    titleNote

    When you use VL recognition module face recognizer, the Maximum performance checkbox is cleared automatically, and the setting becomes inactive when you select the Face recognition server in the previous step. This is due to the feature of this recognizer.

  45. Set the border of the face search area

    46. border

  46. on the video image by specifying the required values in percent in the corresponding fields (3), or by clicking the button (4) and using the interactive interface. After you click the button, the window with the corresponding video camera image

    47. will open

  47. opens. To set the border of the face search area

    48. border, click

  48. :

    1. Click the Stop video button

    49. at

    1. .

    2. Select the required

    50. time, select the required

    1. area using the left mouse button

    51. , and then click OK. The specified face search area border values will

    1. .

    2. Click the OK button. The values of the specified border of the face search area will be automatically entered in

    52. the

    1. the Left, Right, Top and Bottom fields of the Search area border % group.

    53. Image Removed

    1. Image Added

      Note
      titleAttention!

      Setting the border of the face search area

    54. border

    1. is available only

    55. if the Tevian or VideoAxxon PSIM 1.1 face recognition modules are used

    1. for the Recognition module VA and Recognition module VI face recognition modules.

  56. Set the Scaling and selection slider (5) to the position corresponding to the required scale of the captured face in the frame for recording and highlighting the face with a dynamic frame. The current scale value is displayed in the field above the slider and ranges from 1 (only the captured face is recorded) to 5 (the whole frame is recorded).
  57. In the Processing speed, fps field (6), specify how many
    58. fps
  58. FPS from the video stream are processed by the Face detection program module. This parameter is necessary for reducing the load on the
    59. Server
  59. server.

  60. If it is necessary

    61. to convert the

  61. to convert the color video

    62. image to

  62. image to a black-and-white image to generate the vectors by the black-and-white frames, then

    63. uncheck the 

  63. clear the Process color video checkbox (7).

    Note
    titleAttention!

    Generation of vectors by black-and-white frames is supported by

    64. Tevian and VideoAxxon PSIM 1.1 face recognition modules only

  64. the Recognition module VA and Recognition module VI only. It reduces the CPU load, insignificantly affecting the face capture and recognition quality.

  65. By default, the Face

    66. detection tool

  66. detector processes a video with the resolution set for

    67. the 

  67. the Camera

    68.  parent

  68. parent object. To process a video with 320x240

    69. pixels

  69. pixel resolution, set the Process low resolution video checkbox (8).

    Info
    titleNote
    • Enabling this option reduces the load
    70. of
    • on the
    71. Server’s
    • server processor, but the probability of face capture also reduces.
    72. Note
    titleAttention!
    • The Process low resolution video
    73.  setting is not relevant in case,
    • setting isn't relevant when a high resolution is set for
    74. a 
    • the Camera
    75.  parent
    • parent object. Also
    76. this settings is not in use if the Tevian or VideoAxxon PSIM 1.1 module is applied for face capture
    • , this setting isn't used if the Recognition module VA or Recognition module VI module is used to capture a face.

  77. Set the minimum and maximum width and height of the face on the video image in pixels in the corresponding fields of the Face size, pixels group (9).

    Info
    titleNote
    • If the specified minimum dimensions differ significantly from the actual ones, then the faces
    78. will not be captured.
    • won't be recognized by the detector. For example, if the video contains large faces (15-30%), then if you set the minimum size to 5%
    79. ,
    • and the maximum size to 80%,
    80.  then
    • then the faces
    81. will not
    • won't be detected. However, if you specify a minimum size of 12% and a maximum size of 80%,
    82. the
    • faces will be
    83. captured
    • detected.
    • Thus, if the
    85. detection tool
    • detector is configured to capture small faces, then it cannot detect large ones, and vice versa.
    86. info
    87. titleNote
    • If all parameters of face
    88. sizes
    • size are set to 0, the Face Detection
    89. tool
    • module uses similar parameters
    90. set on the Face Recognition Server object settings panel
    • specified on the settings panel of the Face recognition server object (see Configuring the
    91. captured
    92. size
    93. Info
    titleNote
    When using Visionlabs face
    • If you use the VL recognition module, the minimum and maximum values for all face
    94. detection tools should
    • detectors must be the same, as the values are set for the entire software module.
  95. From the Select GPU drop-down list (10), select a video card for recognition for the Recognition module VA and VL recognition module. The Use GPU checkbox must be set on the settings panel of the Face recognition server object (see Configuring the recognition parameters of captured faces).
    Note
    titleAttention!

    All GPUs with Pascal architecture are not supported by the Recognition module VA; if you select such a graphics card, faces will not be recognized.

  96. To save the changes, click the Apply button (
    97. 10)
  97. 11).

Configuration of the basic settings of the Face Detection module is complete.