# minimaxir/person-blocker

Automatically "block" people in images (like Black Mirror) using a pretrained neural network.

Repository: https://github.com/minimaxir/person-blocker
Canonical: https://ross.abutalabs.com/products/person-blocker
Language: Python
License: NOASSERTION
License Family: other
Last push: 2022-09-09T09:46:54+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": 3082, "days_push": 1454, "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 2012, forks 208 (observed 2026-08-28T04:06:05.134219+00:00)

## What it is
A Python command-line script that automatically censors ('blocks') people and up to 80 other object types in images using a pretrained Mask R-CNN model on MS COCO. It outputs both static PNG and animated GIF versions of the blocked image.

## Use cases
- blur out people in photos automatically
- censor faces and objects in images like Black Mirror
- anonymize people in pictures before sharing
- detect and mask specific objects like buses or giraffes in an image
- run object detection on images from the command line without a GPU

## When to choose
- you want automated, no-manual-editing censoring of people or objects in images
- you need a simple CLI workflow and don't have a GPU
- you want both static and animated censored outputs

## When to avoid
- you need production-grade, maintained software - it depends on old TensorFlow 1.x/Keras and sees infrequent updates
- you need video processing rather than still images
- you want fine-grained manual redaction control rather than automatic detection

## Facets
- artifact type: cli-tool
- maturity: maintenance
- function: image-processing, computer-vision, machine-learning
- domain: computer-vision, image-processing, privacy
- platform: python, cli, cross-platform
- tags: mask-rcnn, object-detection, image-censoring, black-mirror, coco, tensorflow

## Member repositories
- minimaxir/person-blocker (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:05.134219+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 2026-08-30T03:01:02.559078+00:00, confidence not recorded.
  - readme: https://github.com/minimaxir/person-blocker (fetched 2026-08-28T04:06:05.134219+00:00, sha 476c955eea8d)
- Data as of 2026-08-30T08:39:29.467469+00:00.