# Star-Clouds/CenterFace

face detection

Repository: https://github.com/Star-Clouds/CenterFace
Canonical: https://ross.abutalabs.com/products/centerface
Language: C++
License: MIT
License Family: permissive
Topics: face-detection, anchor-free, face, ncnn
Last push: 2021-11-12T03:44:00+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2546, "days_push": 1755, "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 1344, forks 351 (observed 2026-08-28T04:04:27.211513+00:00)

## What it is
CenterFace is a lightweight (7.3MB) anchor-free face detection and alignment model that detects faces and predicts facial landmarks using a 'face as point' approach. It ships with C++ (ncnn) and Python inference code optimized for edge devices.

## Use cases
- detect faces in images or video streams
- run face detection on edge devices or mobile
- find facial landmarks alongside bounding boxes
- deploy a small fast face detector with ncnn
- benchmark face detection accuracy on WIDER FACE
- integrate face detection into a C++ application

## When to choose
- you need a tiny, fast face detector for edge or embedded hardware
- you want joint detection and landmark alignment in one model
- you need high accuracy on small/hard faces (WIDER FACE hard set)
- you prefer an anchor-free detection approach

## When to avoid
- you need face recognition or identity matching, not just detection
- you need active maintenance and recent updates (last release 2021)
- you need a general object detector rather than faces only
- you require extensive documentation or community support

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, computer-vision, image-processing
- domain: computer-vision
- platform: cross-platform, python, cpp
- tags: face-detection, face-alignment, anchor-free, ncnn, landmarks, edge-devices, onnx, gpu

## Member repositories
- Star-Clouds/CenterFace (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:27.211513+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 2026-08-30T04:42:48.910274+00:00, confidence not recorded.
  - readme: https://github.com/Star-Clouds/CenterFace (fetched 2026-08-28T04:04:27.211513+00:00, sha 14cbc9b26c10)
- Data as of 2026-08-30T08:39:29.467469+00:00.