Face Detection module basic settings

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

Go to the Basic settings tab on the settings panel of the Face Detection object.
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 of the Face Recognition Server channels. In this case, only capturing of faces detected by Axxon PSIM capturing is performed, and generation of vectors is not performed. This option is not for Face PSIM.
2. External capture is NOT selected but the detection is added to any of the the Face Recognition Server channels. In this case, capturing and saving of photos of faces detected by Axxon PSIM capturing, generation of vectors and recording them to database are performed. This option does not allow face recognition (while search and visitor counting are available).
3. External capture is selected but the detection is NOT added to any of the Face Recognition Server channels. 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 are not saved in the database. This option is only suitable for use in scripts.
4. External capture is selected and the detection is added to any of the Face Recognition Server channels. 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 recorded to the database.
The external capture is recommended for use. From the External capture drop-down list select the Face Recognition Server with the help of which the face capturing 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) and saving of photos will be performed.
Note
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.exe utility for configuring the Cognitec face recognizer section).
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. When this mode is disabled, the memory consumption will decrease, but faces can be missed at capturing.
Set the face search area border 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 will open. To set the face search area border, click the Stop video button at the required time, select the required area using the left mouse button, and then click OK. The specified face search area border values will be automatically entered in the Left, Right, Top and Bottom fields of the Search area border % group.
Attention!
Setting the face search area border is available only if the Tevian or VideoAxxon PSIM 1.1 face recognition modules are used.
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).
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.
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 uncheck the Process color video checkbox (7).
Attention!
Generation of vectors by black-and-white frames is supported by Tevian and VideoAxxon PSIM 1.1 face recognition modules only. It reduces the CPU load, insignificantly affecting the face capture and recognition quality.
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’s processor, but the probability of face capture also reduces.
Attention!
The Process low resolution video setting is not relevant in case, when a high resolution is set for a Camera parent object. Also this settings is not in use if the Tevian or VideoAxxon PSIM 1.1 module is applied for face capture.
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 will not be captured.
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 will not be detected. However, if you specify a minimum size of 12% and a maximum size of 80%, the faces will be captured.
Thus, if the detection tool is configured to capture small faces, then it cannot detect large ones, and vice versa.
Note
If all face sizes are set to 0, the Face Detection tool uses similar parameters set on the Face Recognition Server object settings panel (see Configuring the captured face size for recognition).
Note
When using Visionlabs face recognition module, the minimum and maximum values for all face detection tools should be the same, as the values are set for the entire software module.
To save the changes click the Apply button (10).

Page tree

Documentation for Face PSIM 1.0.1.