# X-zhangyang/Real-World-Masked-Face-Dataset

Real-World Masked Face Dataset，口罩人脸数据集

Repository: https://github.com/X-zhangyang/Real-World-Masked-Face-Dataset
Canonical: https://ross.abutalabs.com/products/real-world-masked-face-dataset
Language: Python
License Family: other
Last push: 2024-11-20T03:08:57+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": 2393, "days_push": 651, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2035, forks 474 (observed 2026-08-28T04:06:07.994594+00:00)

## What it is
A large-scale real-world dataset of masked and unmasked face images, collected and annotated by Wuhan University to support masked face detection, recognition, and verification research. It includes a 525-identity recognition set, simulated masked versions of standard benchmarks (WebFace, LFW, AgeDB-30, CFP-FP), and a verification set of 426 identities with matched/non-matched face pairs.

## Use cases
- train a face recognition model that works when people wear masks
- find a labeled dataset of masked face images
- benchmark face verification accuracy under mask occlusion
- build a mask detection model for access control or gate systems
- evaluate face recognition on masked vs unmasked face pairs
- get simulated masked versions of standard face benchmarks like LFW

## When to choose
- you need real-world photos of people wearing masks with identity labels for training or evaluation
- you want standardized verification pairs comparing masked and normal faces of the same identity
- you need masked variants of established benchmarks such as LFW, AgeDB-30, or CFP-FP
- you are researching occlusion-robust biometrics, e.g. for access control, attendance, or gate recognition

## When to avoid
- you need a working algorithm or codebase rather than data - this repo is primarily a dataset with only demos
- you require a clear open-source license for commercial use - no license is specified in the repository
- you need general face datasets without masks, or very recent post-pandemic data
- your project depends on active software maintenance rather than a static data release

## Facets
- artifact type: dataset
- maturity: stable
- function: machine-learning, computer-vision, image-processing
- domain: computer-vision, machine-learning, deep-learning, image-processing, artificial-intelligence
- platform: python, cross-platform
- tags: masked-face-dataset, face-recognition, face-verification, face-detection, image-dataset, covid-19, benchmark-dataset, occluded-faces

## Member repositories
- X-zhangyang/Real-World-Masked-Face-Dataset (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:07.994594+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 2026-08-30T02:59:20.833411+00:00, confidence not recorded.
  - readme: https://github.com/X-zhangyang/Real-World-Masked-Face-Dataset (fetched 2026-08-28T04:06:07.994594+00:00, sha e38909a7ec9d)
- Data as of 2026-08-30T08:39:29.467469+00:00.