# minivision-ai/Silent-Face-Anti-Spoofing

静默活体检测（Silent-Face-Anti-Spoofing）

Repository: https://github.com/minivision-ai/Silent-Face-Anti-Spoofing
Canonical: https://ross.abutalabs.com/products/silent-face-anti-spoofing
Language: Python
License: Apache-2.0
License Family: permissive
Topics: computer-vision, deep-learning, face-anti-spoofing, android-app, sdk
Last push: 2023-10-03T21:59:14+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2283, "days_push": 1065, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1796, forks 541 (observed 2026-08-28T04:05:37.490017+00:00)

## What it is
An open-source silent face anti-spoofing (liveness detection) project by MiniVision, providing model training code, data preprocessing, test scripts, and pre-trained lightweight MiniFASNet models. It detects whether a face in front of a camera is real or a spoof (printed photo, screen replay, mask) without user cooperation, and ships an Android APK demo.

## Use cases
- detect fake faces from printed photos or screen replays
- add liveness detection to a face recognition pipeline
- train a face anti-spoofing model with Fourier spectrum supervision
- deploy lightweight liveness detection on Android or embedded devices
- test silent liveness detection without user cooperation

## When to avoid
- you need NIR/depth or 3D-structured-light anti-spoofing
- you require production-grade accuracy guarantees (the highest-accuracy model is not open-sourced)
- you need active maintenance and recent updates

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, machine-learning, deep-learning, image-processing, sdk
- domain: computer-vision, security, deep-learning
- platform: python, cross-platform
- tags: face-anti-spoofing, liveness-detection, face-recognition, mobileface, presentation-attack-detection, caffe, onnx, biometrics, android

## Member repositories
- minivision-ai/Silent-Face-Anti-Spoofing (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:37.490017+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:22:49.968355+00:00, confidence not recorded.
  - readme: https://github.com/minivision-ai/Silent-Face-Anti-Spoofing (fetched 2026-08-28T04:05:37.490017+00:00, sha 0282877fb26b)
- Data as of 2026-08-30T08:39:29.467469+00:00.