SpeedFace M1/M2
User Manual
P a g e
| 46
Copyright©2020ZKTECO CO., LTD. All rights reserved.
Face Enrollment
Threshold
During face enrollment, 1:N (One to Many) comparison is used to determine
whether the user has already registered before.
When the similarity between the acquired facial image and all registered facial
templates is greater than this threshold, it indicates that the face has already
been registered.
Face Pitch Angle
The pitch angle tolerance of a face for facial registration and comparison.
If a face’s pitch angle exceeds this set value, it will be filtered by the algorithm,
i.e. ignored by the terminal thus no registration and comparison interface will
be triggered.
Face Rotation Angle
The rotation angle tolerance of a face for facial template registration and
comparison.
If a face’s rotation angle exceeds this set value, it will be filtered by the
algorithm, i.e. ignored by the terminal thus no registration and comparison
interface will be triggered.
Image Quality
Image quality for facial registration and comparison. The higher the value, the
clearer the image will be.
Minimum Face Size
Required for facial registration and comparison.
If an object’s size is smaller than this set value, the object will be filtered and not
recognized as a face.
This value can be understood as the face comparison distance. The farther the
person is, the smaller the face is, and the smaller face pixel will be obtained by
the algorithm. Therefore, adjusting this parameter can adjust the farthest
comparison distance of faces. When the value is 0, the face comparison
distance is not limited.
LED Light Triggered
Threshold
This value controls turn on and off of the LED light. The larger the value, the
more frequently the LED light will be turned on.
Motion Detection
Sensitivity
A measurement of the amount of change in a camera’s field of view that
qualifies as potential motion detection that wakes up the terminal from
standby to the comparison interface. The larger the value, the more sensitive
the system would be, i.e. if a larger value is set, the comparison interface is
much easier and frequently triggered.
Live Detection
Detecting a spoof attempt by determining whether the source of a biometric
sample is a live human being or a fake representation using visible light images.
Live Detection
Threshold
Helping to judge whether the visible image comes from an alive body. The
larger the value, the better the visible light anti-spoofing performance.
Anti-counterfeiting
with NIR
Using near-infrared spectra imaging to identify and prevent fake photos and
videos attack.
WDR
Wide Dynamic Range (WDR), which balances light and extends image visibility
for surveillance videos under high contrast lighting scenes and improves object
identification under bright and dark environments.
