Restrictions and Limitations

System-Wide Restrictions

• Only images in JPG, PNG, JPEG, or BMP format can be recognized.
• Each user can use 10 facial image libraries. Each library contains a maximum of 100,000 facial features.
• Use standard JSON format in the body of the application/json request.
• Do not use carriage return characters in Base64 code.
• The system does not save images or videos of users.

Face Detection/Verification/Retrieval

• The total size of the two images input for face verification is less than 8 MB.

• The image size must be less than 8 MB. If the image size is too large, the image transmission will take a long time. It is recommended that the image size be less than 1 MB.
• The image resolution must be less than 4096 x 2160. The face resolution in an image must be greater than 80 x 80. It is recommended that the face resolution be greater than 120 x 120.
• To ensure the recognition effect, facial images need to meet the following requirements:
  1. The illumination should be greater than 200 lux and there is no light reflection or shadow caused by strong light.
  2. The overall image is clear without obvious motion blur and the face in it is not blocked.
  3. The side face angle does not exceed 30°, and the tilt angle and horizontal angle do not exceed 15°. The face in an image must be a vertically placed front face.

Face LiveDetect

• Currently, only video files and Base64-encoded videos can be detected. User clients need to obtain the video streams, save them as files, and then call the LiveDetect API.
• The size of a video file cannot exceed 8 MB. It is recommended that the video file be compressed to 200 KB to 2 MB on the client.
• The video duration must be 1 to 15 seconds.
• The recommended frame rate is 10 fps to 30 fps.
• The encapsulation format can be MP4, AVI, FLV, WEBM, ASF, or MOV.
• The video encoding format can be H.261, H.263, H.264, HEVC, VC-1, VP8, VP9, or WMV3.