About OCR PDF: get the text out of a scan
A scanned PDF is a picture of a page, so you cannot select or copy its text. OCR (optical character recognition) reads the letters in the image and gives you the text.
Choose the language of the document and start. The recognised text appears on the page to copy, or to save as a .txt or Word .docx file. The recognition runs in your browser.
How to use it
- Choose or drop a scanned PDF.
- Select the document’s language.
- Press Start OCR and wait while each page is read.
- Copy the text or download it as TXT or DOCX.
Good to know
- Languages: English, Hindi, Spanish, French, German, Arabic, Chinese (Simplified) and Russian.
- The language data downloads once, then your browser keeps it.
- The result is plain text. To get an editable document with paragraphs and tables, use PDF to Word with OCR switched on.
- Straight, sharp scans at normal size give the best accuracy. Handwriting is not recognised reliably.
Questions
Does this make my PDF searchable?
No. It extracts the text so you can copy or save it. The PDF itself is not changed.
How accurate is it?
Very good on clear printed text. Accuracy drops with blurred photos, skewed pages, unusual fonts and handwriting.
Why is it slow the first time?
The recognition engine and language data are downloaded once. After that they come from your browser’s cache.
Is my document uploaded?
No. Text recognition runs in this page on your device.