Windows

Faceplugin Face Recognition Windows SDK. Fully on-premise HTTP API on port 8083. detect, quality, feature, match, similarity. No Docker.

Fully on-premise commercial Face Recognition HTTP API for Windows. Default port 8083. Gradio 9003. No Docker on Windows.

This is not the Open Source Face Recognition Windows SDK. For recognition and liveness in the same process, use Face Recognition + Liveness Windows SDK. Or run Face Liveness Detection Windows SDK on port 8084 as a second process.

All processing stays on your server. No biometric data is sent to Faceplugin cloud.

Code

GitHub - Faceplugin-ltd/FaceRecognition-Windows: On-premise Windows Face Recognition SDK with offline 1:1 verification, 1:N identification, face detection, and ICAO quality assessment. Local HTTP REST API + Python bindings. No cloud, full data privacy. Ideal for access control, KYC, and identity verification.GitHub

Setup

Sizing: Hosting requirements.

1

Copy the runtime

Copy the CPU libraries from Google Drive into lib\cpu\.

2

Install and run

pip install -r requirements.txt
run.bat

3

Copy the machine code

curl -s http://127.0.0.1:8083/api/machinecode

Send machine code to Faceplugin. Copy it from the terminal if curl is not available.

4

Activate

curl -s -X POST http://127.0.0.1:8083/api/activate \
  -H 'Content-Type: text/plain' \
  --data-binary @license.txt

Control routes (/api/health, /api/machinecode, /api/activate, /api/licenseStatus) return a JSON envelope. Process POSTs (/api/detect, /api/quality, …) return engine JSON as the HTTP body.

APIs

Same routes as Face Recognition Linux SDK:

Endpoint	Purpose
GET /api/health	Process is listening (no license)
GET /api/machinecode	Machine code
GET /api/licenseStatus	License status
GET /api/backend	"cpu"
POST /api/activate	Activate and init_sdk()
POST /api/detect	Detect faces
POST /api/quality	Quality checks
POST /api/feature	Extract template
POST /api/match	Compare two photos
POST /api/similarity	Compare two templates

Full reference: Face Recognition HTTP API. Shared control routes: Shared endpoints.

Some routes wrap the result in a small JSON object (an envelope). Process POSTs return engine JSON as the body. There is no POST /api/identify (no server-side 1:N gallery).

Try it

curl -s http://127.0.0.1:8083/api/health
IMG=$(base64 -w0 face.jpg)

curl -s -X POST http://127.0.0.1:8083/api/detect \
  -H 'Content-Type: application/json' \
  -d "{\"image\":\"$IMG\"}"

curl -s -X POST http://127.0.0.1:8083/api/match \
  -H 'Content-Type: application/json' \
  -d "{\"image1\":\"$IMG\",\"image2\":\"$IMG\"}"

Postman: import postman/FaceRecognition-API.postman_collection.json from the repo. Base URL http://127.0.0.1:8083. Paths have no /v1.

Gradio (host only): DEMO_PORT=9003 API_BASE=http://127.0.0.1:8083 python demo.py. Open http://127.0.0.1:9003. You do not need Gradio in production.

Request a License & Support · Contact us

FAQ

Face Recognition API on Windows? Yes. Port 8083, same routes as Linux. No Docker.

Offline? Yes after POST /api/activate with a license key bound to this host's machine code.

Related documentation

• Faceplugin Face Recognition Server SDK · Linux · Glossary

• Face Liveness Detection Windows SDK

• ID Document Recognition Windows SDK

• Request a License · Status codes

• Combining products (eKYC) · SDK comparison