minivision-ai/Silent-Face-Anti-Spoofing
A silent liveness detection system that distinguishes real faces from spoofing attacks using deep learning and Fourier spectrum analysis.
Not currently ranked — collecting fresh signals.
star history
This repository provides an open-source silent face anti-spoofing solution that detects whether a face is genuine or fake (e.g., printed photos, screen displays, silicone masks, 3D prints). It includes model training architecture, data preprocessing methods, and test scripts, along with a pruned MobileFaceNet model optimized from 0.224G to 0.081G FLOPs with minimal accuracy loss. The system offers both a classification main branch and a Fourier spectrum auxiliary supervision branch, with an Android APK and SDK for deployment.
Frequently asked
- What is minivision-ai/Silent-Face-Anti-Spoofing?
- A silent liveness detection system that distinguishes real faces from spoofing attacks using deep learning and Fourier spectrum analysis.
- Is Silent-Face-Anti-Spoofing open source?
- Yes — minivision-ai/Silent-Face-Anti-Spoofing is open source, released under the Apache-2.0 license.
- What language is Silent-Face-Anti-Spoofing written in?
- minivision-ai/Silent-Face-Anti-Spoofing is primarily written in Python.
- How popular is Silent-Face-Anti-Spoofing?
- minivision-ai/Silent-Face-Anti-Spoofing has 1.8k stars on GitHub.
- Where can I find Silent-Face-Anti-Spoofing?
- minivision-ai/Silent-Face-Anti-Spoofing is on GitHub at https://github.com/minivision-ai/Silent-Face-Anti-Spoofing.