DeepFace is a lightweight face recognition and facial attribute analysis framework for Python. It wraps state-of-the-art models like VGG-Face, FaceNet, OpenFace, DeepFace, DeepID, ArcFace, Dlib, SFace and GhostFaceNet.
Key features:
- Face Verification: Verifies if two faces belong to the same person.
- Face Recognition: Identifies faces against a database.
- Facial Attribute Analysis: Predicts age, gender, emotion, and race.
- Face Detection: Integrates OpenCV, SSD, Dlib, MTCNN, RetinaFace, MediaPipe, YOLO, YuNet and CenterFace detectors.
- Real-time Analysis: Processes video streams from webcams.
- Similarity Metrics: Supports cosine similarity, Euclidean distance, and L2 normalized Euclidean distance.
- API: Serves functionalities via a REST API.
- Dockerized Service: Easy deployment with Docker.
- Command Line Interface: Access functions via command line.
- Face Anti Spoofing: Detects real or fake faces
