Configuring the captured faces recognition parameters

To set the parameters for the captured faces recognition, do the following:

1. Go to the General settings tab of the Face Recognition Server settings panel.
   
2. Set the Select the best frame for recognition checkbox (1) if from all images of one person which came to the Face recognition server from Face detection it is required to select the best frame and create FIR only for it.
3. In the Similarity level field (2), enter the similarity level of the captured face and the reference image that will be considered a recognized match. The Similarity level parameter value is specified in percent.

4. In the Search for similar faces field (3), enter the maximum number of matching reference images, which identifiers and similarity levels will be stored in database for one frame of a captured face.

   Note

   It is recommended to specify the 1 value for this field for more precise search of the recognized faces (see Filtering the recognized and unrecognized faces).

5. In the Minimum quality for face recognition (0-100) field (4), enter the minimum quality of the captured face in percent, at which the recognition should be performed. The default is 60%.
   

   Important!

   • If Tevian recognition module is in use, it is recommended to set the Minimum quality for face recognition (0-100) value to 60% when updating from Face-Intellect 7.0 to Face-Intellect of later version.
   • If face concealment recognition is enabled, then in order to correctly detect the presence of a face mask, it may be necessary to set the Minimum quality for face recognition (0-100) value below the default value (see Configuring the permissions and additional settings).

6. In the Minimum quality for adding face to DB (0-100) field (5), enter the minimum quality percent for face to be added to the database.

7. By default, the face detectors for which the configured Face Recognition Server is selected as an external capture, generate and attach biometric face parameters to the image. Such procedure is performed if the Create FIR in detection unit checkbox is set (6). If it is necessary that the face detectors only capture the face, and the biometric face parameters are generated by the Face Recognition Server, it is necessary to deselect the Create FIR in detection unit checkbox.
8. Set the Select the best frame in detection unit checkbox (7) if it is required to select the best frames from all images received by Face detectors, for which the configured Face Recognition Server is selected as an external capture, and send only them to the Face recognition server.

9. If it is required to skip repeated recognitions, in the Skip repeated recognitions, sec field (8), set the time period in seconds more than 0 during which a captured face won't be recognized repeatedly. For details, see the IgnoreSamePeople registry key.

   Note

   See Registry keys reference guide, for details about working with the registry, see Working with Windows OS registry.

10. If it is necessary for the recognition to be performed on a discrete graphics card when using the Tevian and VideoIntellect 1.1 face recognition modules, set the Use GPU checkbox (9). Otherwise, the recognition will be performed on the CPU.

    Attention!

    If the Use GPU checkbox is set for the first time, then at the same moment the caching process will start in a new window to optimize the recognition on the current GPU. Do not interrupt this process. If for some reason the caching process was interrupted, it is necessary to delete the folder with the name like "GPU-[video card UUID]" at <Face Intellect installation directory>\ Modules64\Firserver\FaceRecognition\Tevian_ [SDK version]\. Afterwards, when the Use GPU checkbox is set, the recognition using the GPU will be performed immediately without the caching process.

    If you replace the video card, the caching process will restart automatically.

11. In the Collected not less than ... frames with person field (11) enter the minimal number of frames to be collected o one person's face to start the face recognition.

12. In the Person in field of view no less than … seconds field (12) enter the time in seconds upon reaching which the recognition will be performed.

    Note

    The Person left the camera field of view option is always enabled (10).

    Note

     The face recognition starts if at least one of the three conditions (10-12) is met.

13. To save the changes, click Apply (13).

Setting parameters for captured faces recognition is complete.