The Face detection object is created on the basis of the Camera object in the Hardware tab of System settings dialog box.

Configure the Face detection object as follows:

1. Go to settings panel of the Face detection object.
   
2. 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 (1).

3. Set approximate width of face on the video image in percentage of width of frame;

   1. In the From field enter minimally allowable width of face on the video image (2).

   2. In the To field enter maximally allowable width of face  on the video image (3).

4. Set approximate height of face on the video image in percentage of height of frame;

   1. In the From field enter minimally allowable height of face on the video image (4).

   2. In the To field enter maximally allowable height of face  on the video image (5).

      Faces won't be detected if specified minimal sizes highly differ from actual sizes. For example, if there are big faces (15-30%) on the video and minimal size is 5% and maximal size is 80%, then faces won't be detected. But if minimal size is 12% and maximal size is 80%, then faces will be detected. So, detection won't detect big faces if it is configured for detection of small faces, and vice versa.

      Settings of face width and height on the video image is not in use if the Tevian module is applied for face capture.

5. 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 video in low resolution checkbox (6).

   Enabling this option reduces the load of the Server’s processor, but the probability of face detection also reduces.

   The Process video in low resolution 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 module is applied for face capture.

6. Estimate the part of detected faces while processing the video with 320x240 pixels resolution. In case, when this value is not high enough, set the Process video in low resolution checkbox unchecked.
7. Specify the size of a face in percent  relatively to the sizes of camera’s video surveillance window when the face is required to be dynamically framed (7).
8. If the color of a dynamic frame is to be changed, then left click the Color field (8). Select the required color in the standard Color dialog box and click OK.
9. To pixelate the part of video image in which the face was recognized, do the following:
   
   1. To enable the pixelate function set the Pixelate area checkbox (9).

   2. Set the Grain size cursor in position corresponding to the pixilation grain size in pixels (10).

10. Set the Face capture area’s scaling slider to the position corresponding to the required scaling of a face in the frame for recording (11). The current scale value is displayed in the field above the slider and ranges from 1 (only the face is recorded) to 5 (the whole frame is recorded).

    This setting is relevant in case of installed Face Intellect system. A frame with a face is recorded to the < Face-Intellect>\ Bmp\ person\ folder.

11. There are several variations of the face detection operation depending on the setting of the external capture and Face Recognition Server:

    1. External capture is NOT selected and the detection is NOT added to the Face Recognition Server. In this case, only capturing and saving of photos of faces detected by Intellect software capturing is performed, and generation of biometric vectors is not performed.
    2. External capture is NOT selected but the detection is added to the Face Recognition Server. In this case, capturing and saving of photos of faces detected by Intellect software capturing, generation of biometric vectors and recording them to database are performed.
    3. External capture is selected but the detection is not added to the Face Recognition Server. In this case, capturing and saving of photos of faces detected by Cognitec 8.8 or Tevian 1.8.1 capturing and generation of biometric vectors are performed, but the vectors are not recorded to the database.

    4. External capture is selected and the detection is added to the Face Recognition Server. In this case, capturing and saving of photos of faces detected by Cognitec 8.8 or Tevian 1.8.1 capturing, generation of biometric vectors and recording them to the database are performed.

       It is required to enable 64-bit modules if the Tevian module is used for external capture (see Administrator's Guide, the Configuring of using 64-bits modules section).

    The external capture is recommended to be in 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 biometric 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 (12).

    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).

    12. To save the changes click the Apply button (13).

Setting the Face detection is completed.