On this page

Show all

Help Center/ Face Recognition Service/ FAQs/ General Consulting/ What Causes the Low Pass Rate in Face Recognition?

What Causes the Low Pass Rate in Face Recognition?

Updated on 2023-10-19 GMT+08:00

View PDF

The pass rate of face recognition is low. A PU needs to capture multiple images to get one whose score is higher than 0.93 (the threshold).

Qualities of the images in the base library are poor.
The PUs' snapshot conditions are poor.
The face posture captured by the PU is much different from that in the base library, or the face in the base library is much different from that in the snapshot.

Enter the images with good qualities into the base library to replace the poor ones.
Improve the PUs' snapshot conditions. For example, adjust the illumination to avoid backlight. Remove the blurred images and adjust the camera parameters to improve clarity.
If there are too many differences, you can record multiple faces for one person. You can record images with multiple different postures for a face in the base library to ensure that there is a posture similar to the captured one. Alternatively, you can enter captured faces with good qualities into the base library.

Parent topic: General Consulting

Thank you very much for your feedback. We will continue working to improve the documentation.See the reply and handling status in My Cloud VOC.

The system is busy. Please try again later.

Which of the following issues have you encountered?

Content is inconsistent with the product UI

Unclear descriptions

Lack of examples or code

Incorrect steps

Can't find what I need

Lack of best practices

Feedback (optional)

0/500

Select at least one type of issue, and enter your comments or suggestions.

Enter a maximum of 500 characters.

Submit Cancel

For any further questions, feel free to contact us through the chatbot.