For the complete documentation index, see llms.txt. This page is also available as Markdown.

Linux

Faceplugin open-source Face Recognition Linux SDK. Free on-premise Python sample. Lower accuracy than the commercial Docker Face Recognition API.

Code

Free open-source Face Recognition Linux SDK

Overview

Free open-source Face Recognition sample for Linux (Python). Detect faces, extract embeddings, and compare them on your machine — no Faceplugin cloud.

Accuracy is lower than the commercial Face Recognition Linux SDK. Contact Faceplugin if you need the higher-accuracy native engine.

Setup

Please download anaconda on your computer and install it. We used Linux machine without GPU for testing

  1. Create anaconda environment

    conda create -n facesdk python=3.9

  2. Activate env

    conda activate facesdk

  3. Install dependencies

    pip install -r requirements.txt

  4. In face_util/faceutil.py, confirm the Linux library path points to libFaceUtil.so

    (Windows uses '/C/FaceUtil.dll' instead — see the Windows page.)

  5. Compare face images in the test directory

    python run.py

APIs and Parameters

  • GetImageInfo(image, faceMaxCount): returns face bounding boxes, landmarks and feature embedding

  • get_similarity(feat1, feat2): returns similarity between two feature embeddings. 0 to 100

  • Threshold: value to determine if two embeddings belong to same person, default = 75

FAQ

Same accuracy as Docker Hub? No. Use Face Recognition Linux SDK (faceplugin/face-recognition) for the commercial Face Recognition API.

Last updated