How to make a scanned PDF searchable with OCR
Turn scans and photos into PDFs you can search, copy and read aloud, with tips to get accurate results.
Why you cannot search a scan
A scanner or a phone camera produces pictures of pages. A PDF made of pictures looks like text, but for the computer it is just an image: search finds nothing and you cannot copy a sentence.
What OCR does
Optical character recognition analyses the image, recognises letters and words and writes them into the PDF as an invisible layer placed exactly over the original. The page looks the same, but now it can be searched, selected, read aloud and converted to Word.
Prepare a good scan
Accuracy depends on the input. Use good light, keep the sheet flat and straight, and use the Document filter of the Scanner to get a clean white background. A resolution equivalent to 200–300 dpi is ideal.
Run OCR
Open the OCR tool, choose the file and the language of the text (you can combine more than one), then start. Pages that already contain text are skipped, so mixed documents are processed quickly.
Check the result
Search for a few words that appear in the document. Small errors can happen with tiny fonts, decorative typefaces or handwriting, which OCR does not read reliably.
Offline and private
The recognition engine runs on your device; only the language model is downloaded once. Your documents are never sent to a server.