Amazon Rekognition Face Liveness now returns Feedback Codes
Hi everyone, Shii-chan here! Today's news makes identity verification a little kinder.
AWS What's New
aws.amazon.com
What was announced?
AWS What's New announced that Amazon Rekognition Face Liveness now returns Feedback Codes. They explain why a liveness check received a low score and how users could retry successfully.
The story so far
Rekognition Face Liveness verifies that the person in front of the camera is a real, live human, and not a photo, video replay, mask, or deepfake, through a short, guided selfie-video check. It returns a confidence score, a reference image for face matching, and session audit images. But when the score was low, it was hard to tell why.
What changes
The codes are returned in the GetFaceLivenessSessionResults API response. They identify the specific conditions that contributed to the low score, such as:
- Poor lighting
- Face obstruction
- Closed eyes
- Low video quality
A single session can return multiple Feedback Codes at once, so users can resolve all contributing issues in one retry.
Dive Deep
The announcement calls out these use cases:
- Identity verification onboarding
- Re-authentication flows
- Accessibility scenarios
Customers can surface these codes to their end users, who can make targeted corrections and retry with confidence.
Regional availability:
- US East (N. Virginia)
- US West (Oregon)
- Europe (Ireland)
- Asia Pacific (Tokyo, Mumbai, Malaysia, Thailand)
- South America (São Paulo)
For the specific list of codes, see the Amazon Rekognition Face Liveness API documentation and FAQ.
Wrap-up
- Face Liveness returns Feedback Codes that explain low scores
- The codes come in the
GetFaceLivenessSessionResultsresponse - Multiple codes can come back at once, so one retry can fix everything
- Especially useful for identity verification, re-authentication, and accessibility
This is for anyone building identity verification flows who wants fewer users dropping off!
