Blur license plates

Make number plates unreadable before you post a photo – for the sales ad, a forum or social media. The tool finds plates, signs and other text automatically, smaller ones in the background too, and covers faces along the way. Pixelate, blur or a black bar; whatever is missing you drag yourself. Everything happens in your browser, with no upload and no third parties.

🔒 No upload – your photos never leave your device
    Effect
    Shape
    Higher also finds small and side-on faces – but more false hits, too.

    Text and plate search PP-OCR, face detection YuNet · one-time ≈ 22 MB from mytoolio.org

    ✓ Metadata such as GPS location and camera data is removed when saving.

    No photo yet. Drop an image here – number plates, text and faces are found and pixelated automatically.

    Tap a frame to switch it off or on. Drag across the image to add an area – e.g. for number plates or name tags. Frames can be moved; the bottom-right corner resizes them.

    Ready

    How it works

    1

    Choose photos

    Drop one or more photos into the box, pick them or paste them with Ctrl+V. They are only read locally.

    2

    Check the areas

    Plates, text and faces are found and covered automatically. Tap a frame to leave a spot visible, or drag areas of your own.

    3

    Adjust & save

    Pick the effect and strength and save the image – several photos at once as a ZIP. Metadata such as the GPS location is removed.

    Frequently asked questions

    Are my photos uploaded?+

    No. Your photos are only read in your browser, searched and edited there – they never leave your device. The detection and its runtime come from mytoolio.org itself; there are no requests to other services.

    Does it find every plate?+

    It finds readable plates reliably, several per photo and smaller ones on cars in the background too. It can miss very small plates, ones shot at a steep angle, dirty or partly hidden ones. So check every picture and simply drag the missing spots yourself – one frame is enough.

    Why is other text marked as well?+

    The detection looks for text of any kind, not just number plates: it also marks shop signs, house numbers, stickers or billboards, and occasionally patterns that look like writing. Tap a frame to switch it off; “All off” switches everything off so you only turn the wanted spots back on. The tool deliberately does not use a dedicated plate model, because the available ones do not come with a licence that suits this site.

    Which effect is the safest?+

    A bar is the safest because it covers everything. Pixelating and blurring are built here so that only a few coarse colour blocks remain – the characters cannot be reconstructed from them. Choose the strength so that no digit can be guessed any more.

    Do I have to hide number plates at all?+

    That depends on the country; in Germany, for example, there is no general duty, since a plate alone does not tell private individuals who owns the car. It is still common and sensible – in sales ads, so nobody misuses the plate, or when photo and text together point to a person. With pictures of other people’s vehicles, pixelating keeps you on the safe side. This is not legal advice.

    What happens to the metadata?+

    When saving, the image is created anew. All metadata is dropped in the process – including the GPS location, the camera model and the time taken. The original photo on your device stays unchanged.

    Does it work with videos too?+

    In videos only faces are currently found automatically and tracked over time; plates are only detected in photos. If a plate stands still in a video, after the first run you can drag a rectangle over it with “Check faces” – it stays covered for the whole video. For dashcam footage you can edit single frames as photos.

    Text and plate search with the PP-OCRv4 text detector (PaddleOCR, Apache 2.0), face detection with YuNet (OpenCV Model Zoo, MIT) via ONNX Runtime Web (MIT) – all served by mytoolio.org and run entirely in your browser. The detection can miss spots; please check every image before sharing.