Privessa

Auto Blur Licence Plates

Recognise the text of a licence plate and cover it.

Redaction & masking Heavy client-side (WASM) tesseract.js OCR + plate shape heuristic + Canvas

Tool preview

How to use it

  1. 01

    Drop a photo of a vehicle.

  2. 02

    Plate-like text is recognised and covered.

  3. 03

    Download the result.

Limitations

FAQ

Why use OCR instead of a plate model?

A plate-specific model is several MB on its own. Recognising the text and filtering by shape keeps the download smaller and covers the same common cases.

It covered a sign instead of the plate. What now?

Check the preview: any text that looks like a plate is covered. Use the manual blackout tool for precise control.

Is the photo uploaded?

No.

Files never leave your device

Processing happens in your browser using the File API, WebAssembly and Web Workers. There is no upload endpoint.

Technical details

Processing
Heavy client-side (WASM)
Implementation
tesseract.js OCR + plate shape heuristic + Canvas
Category
Redaction & masking
Network requests
None while processing

Related tools