Open-source facial recognition service with REST API and Docker deployment
- Stars8k
- Forks1.1k
- Open Issues234
Apache-2.0
- Java
- TypeScript
- Python

About CompreFace
CompreFace is a free and open-source facial recognition service for face recognition, verification, and detection. It is meant to be integrated into existing systems without prior machine learning skills, and it can run as a standalone server or be deployed in the cloud.
It provides a REST API for face recognition, face verification, face detection, landmark detection, mask detection, head pose detection, age recognition, and gender recognition. It ships as a docker-compose setup and supports CPU and GPU models. The UI includes role management for controlling access to face recognition services.
CompreFace is open source under the Apache 2.0 license. It is based on FaceNet and InsightFace and is designed for self-hosted use. Linux, macOS, and Windows setup paths are available through Docker or Docker Desktop, with local access on port 8000.
Key features
- REST API for face recognition, verification, and detection
- Landmark, mask, head pose, age, and gender recognition
- Docker-compose deployment with CPU and GPU models
- Role management for access control
- Standalone server or cloud deployment
Details
- First released
- 2020
- Platforms
- Windows · macOS · Linux
- Deployment
- self-hostable · docker · cloud
- License
- Apache 2.0
- APIs
- REST API
- Models
- CPU · GPU
