The performance is not adequate, what else can I configure?
To ensure proper functioning of AI-Bio you should position the camera in a frontal position with respect to the faces to be framed at an height of 1.8m circa. The camera has to be positioned so that the face of the person takes up an area of 30x30 pixels at least. It is advisable to draw the person's eyes to the camera (for instance with the aid of displays) to maximize the probability of detecting the face. For the very same reason, it is advisable to use a camera suitable for hiding (eg.: pinhole on a merchandiser).
In the drop-down menu on the left, by selecting "Algorithm parameters" and then“Face Detection” you can add, remove and edit areas for face detection inside the scene framed by the camera. Specifically, by clicking on “Add sensor”, you can draw a virtual coil inside the image through "Redraw the sensor", until a coil of desired dimensions is drawn. After having added a sensor it is possible to configure the following parameters:
To reduce the number of false positives and increase the reliability of the plugin it is vital to specify maximum and minimum width and height of the face by drawing some rectangles on the image on the left side. Click on the blue pencil to do so. Moreover, in the face detection session it is possible to enable notifications of the event everytime the app detects a face.