User's Manual

4-inch Visible Light Terminal User Manual
Page | 49 Copyright©2020 ZKTECO CO., LTD. All rights reserved.
Function Description
Function Name
Description
1:N Match Threshold
Under 1:N
verification mode, the verification will only be successful when the
similarity between the acquired facial image and all registered facial templates
is greater than the set value.
The valid value ranges from 65 to 120. The higher the thresholds, the lower the
misjudgment rate, the higher the rejection rate, and vice versa.
It is
recommended to set the default value of 75.
1:1 Match Threshold
Under 1:1 verification mode, the verification will only be successful when the
similarity between the acquired facial image and the user’s facial templates
enrolled in the device is greater than the set value.
The valid value ranges from 55 to 120. The higher the thresholds, the lower the
misjudgment rate, the higher the rejection rate, and vice versa.
It is
recommended to set the default value of 63.
Face
Enrollment Threshold
During face enrollment, 1:N comparison is used to determine whether the user
has already registered before.
When the similarity between the acquired facial image and all registered facial
templ
ates 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 exceed
s 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 requires.
Minimum Face Size
Required for facial registration and comparison.
If the minimum size of the captured figure is smaller than this set value, then it
will be filtered off 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 the face pixel will be obtained
by the algorithm. Therefore, adjusting this parameter can adjust the furthest
comparison distance of faces. When the value is 0,
the face comparison
distance is not limited.