# ORB-HD/deface

Video anonymization by face detection

Repository: https://github.com/ORB-HD/deface
Canonical: https://ross.abutalabs.com/products/deface
Language: Python
License: MIT
License Family: permissive
Topics: face-detection, video-anonymization, human-faces, video-processing
Last push: 2024-10-13T21:56:24+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2386, "days_push": 689, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1558, forks 173 (observed 2026-08-28T04:05:03.591467+00:00)

## What it is
deface is a Python command-line tool that automatically anonymizes human faces in videos and photos. It detects faces in each frame and applies blurring or black-box filters, discarding audio tracks by default.

## Use cases
- blur faces in a video before publishing it online
- anonymize people in street interview footage
- redact faces from photos for GDPR compliance
- anonymize webcam feed in real time
- batch-process video files to remove identifiable faces
- replace faces with black boxes instead of blur

## When to choose
- you need a simple, automated CLI tool for face anonymization in videos or images
- you want cross-platform, pip-installable software with no GUI overhead
- you need live camera anonymization or batch processing of video files
- you prefer an MIT-licensed open-source tool over manual video editing

## When to avoid
- you need to anonymize other identifying features like license plates, tattoos, or voices
- you require a graphical interface for frame-by-frame manual redaction
- you need guaranteed perfect detection of every face in challenging footage
- you need to preserve audio tracks (they are discarded by default)

## Facets
- artifact type: cli-tool
- maturity: stable
- function: video-processing, computer-vision, privacy, cli
- domain: privacy, computer-vision
- platform: windows, python, cli, cross-platform
- tags: face-detection, face-blurring, anonymization, gdpr, video-redaction, video, command-line, linux, macos

## Member repositories
- ORB-HD/deface (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:03.591467+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 2026-08-30T04:29:52.827914+00:00, confidence not recorded.
  - readme: https://github.com/ORB-HD/deface (fetched 2026-08-28T04:05:03.591467+00:00, sha 1e8b1a5b3382)
  - registry_pypi: https://pypi.org/pypi/deface/json (fetched 2026-08-29T11:29:49.847597+00:00, sha d2fea97c9d90)
- Data as of 2026-08-30T08:39:29.467469+00:00.