Basic settings of the Face Detection module

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

1. Go to the Basic settings tab on the settings panel of the Face Detection object.
   

2. There are several variations of the face detection operation depending on the setting of the external capture and Face recognition server (1):

   1. External capture is NOT selected and the detection is NOT added to any channel of the Face recognition server. In this case, faces are captured by Axxon PSIM face capturing, and vectors aren't generated. This option isn't used in Face PSIM.
   2. External capture is NOT selected, but the detection is added to some channel of the Face recognition server. In this case, the photos of captured faces are captured and saved by Axxon PSIM face capturing, the vectors are generated and saved to the database. Face recognition isn't available with this option (the search and visitor counting are available).
   3. External capture is selected, but the detection is NOT added to any channel of the Face recognition server. In this case, the photos of faces captured by the face recognition modules (see Structure of the Face PSIM software package) are captured and saved, and the vectors are generated, but the vectors aren't saved to the database. This option is only suitable for use in scripts.

   4. External capture is selected, and the detection is added to any channel of the Face recognition server. In this case, the photos of faces captured by the face recognition modules (see Structure of the Face PSIM software package) are captured and saved, and the vectors are generated and saved to the database.

   We recommend using the external capture. From the External capture drop-down list, select the Face recognition server that will capture faces with the subsequent generation of a vector (if the Create FIR in detection unit checkbox is set on the settings panel of the corresponding Face recognition server object—see Configuring the Face recognition server object) saving of photos.

   Note

   Correct configuration of the Face recognition server selected as external capture is performed with the help of the Cfgedit.exe utility (for the detailed information about this utility, see Cfgedit.exe utility for configuring the Cognitec face recognizer).

3. 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. If you disable this mode, the memory consumption decreases, but faces can be missed when capturing.

4. Set the border of the face search area 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 opens. To set the border of the face search area:

   1. Click the Stop video button.

   2. Select the required area using the left mouse button.

   3. Click the OK button. The values of the specified border of the face search area will be automatically entered in the Left, Right, Top and Bottom fields of the Search area border % group.
      

      Attention!

      Setting the border of the face search area is available only for the VA and VideoIntellect 1.1 face recognition modules.

5. 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).
6. In the Processing speed, fps field (6), specify how many FPS from the video stream are processed by the Face detection program module. This parameter is necessary for reducing the load on the Server.

7. If it is necessary to convert the color video image to black and white image to generate the vectors by the black-and-white frames, then clear the Process color video checkbox (7).

   Attention!

   Generation of vectors by black-and-white frames is supported by the VA and VideoIntellect 1.1 face recognition modules only. It reduces the CPU load, insignificantly affecting the face capture and recognition quality.

8. By default, the Face detection tool processes a video with the resolution set for the Camera parent object. To process a video with 320x240 pixels resolution, set the Process low resolution video checkbox (8).

   Note

   • Enabling this option reduces the load of the Server processor, but the probability of face capture also reduces.
   • The Process low resolution video setting isn't relevant when a high resolution is set for the Camera parent object. Also, this settings isn't used if the VA or VideoIntellect 1.1 module is used to capture a face.

9. 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).

   Note

   • If the specified minimum dimensions differ significantly from the actual ones, then the faces won't be recognized by the detection tool. For example, if the video contains large faces (15-30%), then if you set the minimum size to 5%, and the maximum size to 80%, then the faces won't be detected. However, if you specify a minimum size of 12% and a maximum size of 80%, faces will be detected. Thus, if the detection tool is configured to capture small faces, then it cannot detect large ones, and vice versa.
   • If all parameters of face size are set to 0, the Face Detection module uses similar parameters specified on the settings panel of the Face recognition server object (see Configuring the size of a face for recognition).
   • If you use the VisionLabs face recognition module, the minimum and maximum values for all face detection tools must be the same, as the values are set for the entire software module.
10. From the Select GPU drop-down list (10), select a video card for recognition for the Tevian and VisionLabs modules. 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).
    

    Attention!

    GeForce GTX 1060 GPU is not supported by the Tevian module; if you select this graphics card, faces will not be recognized.

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