How does a face scan work, from a technical standpoint?Updated a year ago

- Face detection / quality control

A video camera records a short video feed of the face. Using various algorithms, this video is corrected for facial and camera movements. The recording conditions (e.g. light) are automatically checked to ensure a qualitative measurement.

- ROI detection

Small facial areas (ROI) with good skin blood flow are selected.

- Biomedical signal selection.

Ambient light penetrates the skin and reflects off the blood vessels. The pixel values in the facial ROI are used to construct a raw signal. This signal contains small color changes, derived from the heartbeat, which are essential for measuring health parameters.

- Signal processing/machine learning

The raw signal is converted into a qualitative photoplethysmogram (PPG) waveform and facial micro-expression patterns using innovative signal processing and machine learning techniques.

- Health parameters

Health parameters are accurately calculated from this waveform using unique IntelliProve algorithms.