DocumentationAPI Reference
Help CenterAPI ChangelogOpenAPI SpecStatus
API Reference
Help CenterAPI ChangelogOpenAPI SpecStatus

Selfie Verifications

A Selfie Verification answers the question "Is the individual present during the transaction?". This is especially useful when combined with a Government Id Verification to associate the face of the government issued id to the individual present

The main goals of Selfie Verifications are to ascertain the following:

  1. Face Image Quality
    1. Poses - Determine whether an individual is properly facing towards the camera
    2. Quality - Determine whether the the image's resolution, lighting, and blur is sufficient for accuracy
    3. Obfuscation - Determine that and individual's portrait is not obfuscated by glasses, hair, or other items
  2. Face Comparison
    1. Determine whether the individual matches a claimed individual
  3. Face Liveness
    1. Determine whether the submission contains features that are indicative of a spoof

Selfie Capture Types

  1. Center only - Only one portrait of the individual facing the camera is captured

  2. Center and profile - Three portraits are required captured the individual facing left, center and right of the camera

Verification Checks

See the full set of Selfie Verification checks in the Verification Checks table in your Dashboard.

Product Versions

Match

VersionNotes
3.2.0Add support for Digital ID matching
3.1.2Reduce false rejections caused by low quality ID portraits
3.1.1Bug fix for cross product interoperability
3.1.0Improve support for NFC match
3.0.0Major version update of face comparison ensemble model

Liveness

VersionNotes
3.3.0Significant improvements for injection attacks
3.2.0Significant false positive rate improvements. Adjust risk levels to account for new ensemble model score shifts.
3.1.0Significant false positive rate improvements. Adjust risk levels to account for new ensemble model score shifts.
3.0.1Significant false positive rate improvements. Adjust risk levels to account for new ensemble model score shifts.
3.0.0Major version update that includes improved deepfake and generative AI recall
2.2.0Significant false positive rate improvements. Adjust risk levels to account for new ensemble model score shifts.
2.1.0Improve auto-capture experience
2.0.0Major version update of face Presentation Attack Detection ensemble model

Age

VersionNotes
2.2.1Enforce stricter face quality. Exclude adverse face positioning and illuminations by default
2.2.0Minor version update of Age estimation ensemble model
2.1.2Expose additional risk configuration settings
2.1.1Improve low image quality handling
2.1.0Broader rollout of new checks:
selfie_age_threshold_comparison
id_age_inconsistency_detection
2.0.0Launch new Selfie age estimation model