Face Verification (v2)

API reference

curl -X POST "https://__mock__/v2/face_verification/verify" \  -F file="string"

{
  "confidence": 0.1,
  "face_detected": true,
  "faces_found": 0
}

{
  "msg": "string"
}

{
  "detail": {},
  "message": "string"
}

{}

Overview

Call POST /v2/face_verification/verify with Authorization: Bearer <token> and multipart/form-data. Required: file. Optional: unique_id. The response includes confidence, face_detected, and faces_found when verification succeeds.

Key features

• Quality gate: Confirms a usable face and quantitative confidence before you spend facematch or liveness quota.

Implementation

Step 1: Prepare a face crop or selfie frame

Send a single-subject image; very small or oblique faces may fail validation.

Step 2: Call from your backend

POST /v2/face_verification/verify HTTP/1.1
Host: <machine-learning-api-base-url>
Authorization: Bearer <token>
Content-Type: multipart/form-data; boundary=----boundary

Error handling

Benefits

• Surfaces structured verification output for automated onboarding rules.

Next steps

• Facematch
• Crop Face