To configure face detection tool, do as follows:

  1. Select the Face Detection object. 

  2. Configure parameters of face detection tool.

    ParametrDescription
    EnableEnable/disable detection tool.
    Real-time recognitionIf you require using this detection tool for real-time facial recognition, activate this parameter.
    Record Objects tracking

    If you need to enable recording of metadata, activate this parameter.

    Age and genderIf you need to save age and gender information for each recognized face, activate this parameter.
    Decoder mode 

    Select a processing resource for decoding video streams. When you select a GPU, a stand-alone graphics card takes priority (when decoding with NVidia NVDEC chips). If there's no appropriate GPU, the decoding will use the Intel Quick Sync Video technology. Otherwise, CPU resources will be used for decoding.

    Filter false alarmsIn some cases, the detection tool may take other object for a face. To filter out non-facial objects, activate this parameter while calculating the vector model of a face and its recording into the metadata DB. If the filtering is on, false results will appear in the detection feed but will be ignored during searches in Archive.
    Frame processing period

    Set the time (in milliseconds) between face search operations in a video frame. Acceptable values range: [1, 10000]. Increasing this value decreases the Server load, but can result in some faces being missed. 

    Frame size change

    Analyzed framed are scaled down to a specified resolution ( 1280 pixels on the longer side). This is how it works:

    1. If the longer side of the source image exceeds the value specified in the Frame size change field, it is divided by two.

    2. If the resulting resolution falls below the specified value, it is used further.

    3. If the resulting resolution still exceeds the specified limit, it is divided by two, etc.

    Maximum face width

    Maximum face height

    Minimum face width

    Minimum face height

    		Specify the minimum and maximum sizes of detectable faces in % of the frame size.
    Minimum threshold of face authenticitySet the minimum level of face recognition accuracy for the creation of a track. You can set any value by trial-and-error; no less than 90 is recommended. The higher the value is, the fewer faces are detected, while recognition accuracy increases.
    Mode Select the processor for the face detection − CPU or NVIDIA GPU.
    Track loss timeEnter the time in milliseconds after which the face track is considered to be lost. Acceptable values range: [1, 10000]. This parameter applies when a face moves in a frame and gets obscured by an obstacle for some time. If this time is less than the set value, the face will be recognized as the same.
    Face detection algorithm

    Select a recognition algorithm:

    1. ALG1 is faster but less accurate while
    2. ALG2 is more accurate but relatively slower.
    Minimum face recognition quality

    Set the minimum quality of a facial image for recognition. Set the value by trial-and-error, values over 50 are recommended.

    Minimum filtering threshold

    If you need to filter out false positives, set the minimum percentage of probability which makes the algorithm identify a track as a human face. If the algorithm takes a decision that the track relates to a face with a probability value lower than the specified threshold, the track will be ignored. Set the value by trial-and-error, values over 50 are recommended.


  3. Select the Area for detection object. 
  4. Select a rectangular area to be searched for faces in the preview window. To select the area, move the intersection points .
  5. Click  to save changes.

The detection tool is now configured.