This project aims to build a production-ready, real-time face recognition system with sub-100ms latency via WebRTC streaming while maintaining high-accuracy detection and embedding matching.

01 / OBJECTIVEProduction-ready identity verification

This project aims to build a production-ready, real-time face recognition system. The focus is on achieving sub-100ms latency via WebRTC streaming while maintaining high-accuracy detection and embedding matching.

02 / STACKCore technology stack

The system utilizes the InsightFace buffalo_l model pack (SCRFD detector + ResNet-50 ArcFace). Real-time performance is achieved using Gradio 5.x with FastRTC, removing standard HTTP polling latency.

03 / FOUNDATIONSML foundations

The architecture leverages 512-dimensional normalized embeddings. By applying ArcFace (Additive Angular Margin Loss), the model ensures highly discriminative embeddings, even in variable lighting. Inference is accelerated via ONNX Runtime for efficient cross-platform execution.

04 / ROADMAPDevelopment roadmap

  • Completed: Architecture design and tech stack selection.
  • In Progress: FaceRecognizer implementation and WebRTC integration.
  • Planned: Anti-spoofing implementation, CI/CD pipeline, and full production deployment.
Project status

This project is currently under active development.