Image & PDF OCR

Recognize text in local images or selected PDF pages using a selected language.

Processed on your device

Your files

Choose files from your device50 MiB per file, up to 50 files and 100 MiB combined. Files stay in this tab.Drag and drop files here, or browse below.

Options

Options
Choose the language of the text in the document to improve recognition.
Dots per inch control rendering detail. Higher values make sharper images but use more memory and create larger files.

How to use this tool

  1. Choose the local files you want to use for image & pdf ocr.
  2. Adjust the labelled settings, then run the tool. Recognize text in local images or selected PDF pages using a selected language.
  3. Review the result before copying or downloading it. Clear the tool when finished.

Things to know

  • Maximum 50 MiB per PDF, 100 MiB combined and 500 pages. Encrypted documents are unsupported. Page composition preserves visible page content, not document-level forms, bookmarks or attachments. Newly added text uses standard Latin PDF fonts. PDF objects, final PDF output, ZIP exports and rasterized compression candidates are limited to 64 MiB before final packaging. Text extraction is limited to 4 MiB of characters. Editing and attachment extraction limit decoded streams to 32 MiB each, 128 MiB combined, 100000 objects, one million parsed values and 128 nesting levels.
  • The selected local language engine downloads before use. Maximum 50 pages and 4 MiB of recognized text; recognition can contain errors. Output is TXT, not a searchable PDF.

You might also need

More in pdf & documents