Face Crop (v2 YOLO)

API reference

curl -X POST "https://__mock__/v2/yolocrop/face" \  -F file="string"

"string"

{
  "msg": "string"
}

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

Overview

Call POST /v2/yolocrop/face with Authorization: Bearer <token> and multipart/form-data. Required: file. Optional: unique_id. Success returns image/jpeg bytes.

Key features

• Model refresh: Provides an alternative crop path to Crop Face for deployments that enable the v2 YOLO stack.

Implementation

Step 1: Capture a scene with a clear face

Avoid heavy occlusion when possible.

Step 2: Call from your backend

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

Error handling

Benefits

• Produces normalized face chips for downstream facematch or liveness.

Next steps

• Crop Face (v1)
• Facematch