Skip to main content
Didit’s Biometric Authentication solution provides a streamlined verification experience for returning users. This workflow can be configured to perform a liveness-only check for simple presence verification, or combine liveness with facial recognition for stronger identity confirmation against a stored portrait. This flexibility creates a frictionless experience while maintaining high security standards.

​
Key Features

​
Fast Re-Verification

  • No document scanning required
  • Complete verification in seconds
  • Reduces user friction and abandonment

​
Advanced Security

  • Uses the same neural network architecture as Face Match 1:1
  • Prevents account takeover attempts
  • Includes liveness detection to prevent spoofing

​
Integration Flexibility

  • Available as web-based
  • Configurable matching thresholds
  • Optional Device & IP Analysis for enhanced security

​
How It Works

Session Creation

When you create a biometric authentication session for a workflow with face matching, Didit needs a reference face to compare the live selfie against. You have two options:
  • Send portrait_image in Base64 (max 2MB) from your own database. It always takes precedence when provided.
  • Omit portrait_image and pass the user’s vendor_data. Didit automatically reuses the face already stored for that user, resolved in this order:
    1. Face captured during an approved liveness check
    2. ePassport chip photo from an approved ID verification
    3. Portrait cropped from the ID document of an approved ID verification
    4. Manually enrolled profile face (Users API or Console upload)
Only faces from approved sessions (or faces you enrolled yourself) are ever reused. If you omit portrait_image and the user has no stored face, session creation fails with 400 and the message No stored face image was found for this user. Send a portrait_image, or complete an approved verification with face liveness or an ID document for this vendor_data first. If you omit vendor_data as well, the 400 message asks you to send a portrait_image or a vendor_data with a stored face.

Live Photo Capture

During the authentication process:

Verification & Result Processing

The system processes the verification based on your workflow configuration:
If Face Match is disabled in the workflow, the system only confirms the user’s liveness; no reference face is needed and portrait_image is not required. A successful check results in an approved authentication, useful for simple presence verification.
If Face Match is enabled in the workflow (reference face from portrait_image or the user’s stored face):
  1. System performs the liveness check first
  2. If liveness passes, compares the new selfie with the reference face
  3. A similarity score (0–100%) is generated
  4. Score above your configured threshold → Approved
  5. Score below threshold → Declined
Results are available via API response, Business Console, and webhooks.