The performance of BriefCam facial recognition on people wearing face masks, showed an expected drop in reliability due to drops in face extraction and face matching accuracy. This is because a facial mask covers a significant part of the face and the algorithm has fewer facial landmarks to analyze.

Therefore, although BriefCam’s face recognition performs correctly on some instances of masked faces – it will be less accurate and less reliable for most operational scenarios.

Face Mask Detection Guidelines

Like in Face Recognition, the best results for face mask detection are achieved when the camera is at eye-level, at a shallow angle, and with no occlusions and good lighting.

Face mask detection requires a captured face quality of at least 1-star. This also means that the face resolution should be more than 40x40 pixels across the face.

Accuracy should be above 90% in scenes with good conditions (good lighting and resolution as well as a small pitch and yaw of the faces).

Examples of Conditions

	bad lighting and resolution
	bad angle (yaw) but good quality
	bad image quality and angle
	bad resolution, quality, and illumination (and a person with stubble)
	non-face recognition quality
	good quality (some tough angles)