Photo Scrubber — local face blur & metadata removal
- ID
- 30545
- Status
- summarized
- Published
- 30 Sep 2026, 12:45 AM
- Fetched
- 01 Oct 2026, 6:35 AM
- Provider
- Simon Willison
- Category
- developer-ai
- Original URL
- https://simonwillison.net/2026/Sep/29/photo-scrubber/
- Source URL
- https://simonwillison.net/atom/everything/
Summary
- Score
- 6.0
- Created
- 01 Oct 2026, 6:36 AM
- Tags
- Audience
- developersvibe_codersai_ml_learners
What happened
Simon Willison published Photo Scrubber, an experimental browser tool that automatically detects and blurs faces and strips metadata from photos. He built it with GPT-6 Astra after taking a photograph of protesters and deciding he did not want to share images of strangers with identifiable faces. The detection stack is Google's MediaPipe C++ library compiled to WebAssembly via @mediapipe/tasks-vision, running the BlazeFace face detection model.
Why it matters
It is a working example of face detection running entirely in the browser via MediaPipe WASM, which means photos are never uploaded to a server — useful if you publish images containing bystanders or clients and do not want to route them through a third-party API. The post gives no accuracy numbers or false-negative rate, so treat auto-blur as a first pass you verify by eye before publishing anything, not as anonymisation. The reusable part is the stack choice: @mediapipe/tasks-vision plus BlazeFace is a small, self-hostable detection path you can drop into your own upload pipeline.
Discussion angle
BlazeFace is a lightweight detector — how much manual review would you budget before trusting an automatic blur on a photo you intend to publish, and where does the browser-side WASM approach stop scaling versus a server-side model?