Face masking at export

The AviExport utility allows face masking in the exported video. This function is based on neural network.

Perform the following settings to make the face masking function:

1. Install Detector Pack 2.6 or newer. The installation kit and documentation are available on the AxxonSoft web site: https://www.axxonsoft.com/resources/downloads/intellect.php
2. Enable 64-bit modules – see Configuring of using 64-bits modules
3. Select export with data conversion and recompression in the AviExport utility – see Select export mode

As a result of the above steps, the Face masking checkbox becomes available. If it is set, then a mask appears over the faces in the exported file.

Example masking in the exported video:

This function is configured using the SmallFacesDetector.config configuration file located in the Intellect software installation directory in the Modules64/caffewrapper folder. The following options can be configured:

• mode – calculation mode: CPU or GPU.
• deploy_file, model_file – neural network configuration file. At the time of this instruction publishing, there are only those configuration files that are used by default, so it is not required to change these parameters.
• count_classes – number of classification classes (default 2). Do not change this setting.
• trek_trsh – new face tracking threshold (default 0.2). After exceeding this threshold, face tracking is carried out taking into account the result_filter parameter.
• result_filter – confidence threshold (default 0). If the result of face recognition on the exported video is reliable with a probability above the specified threshold, then the face is considered detected. The higher the value, the less likely the false face recognition, but the greater the likelihood of skipping.