Skip to content

OCR

OCR (optical character recognition) is the technique that turns an image of text — a scanned page, a photo of a receipt — into real text: the kind you can select, copy and search. To a computer, a scanned PDF is just a photograph; it has no idea what letters are on it. OCR analyses the pixels, recognises the shapes of the letters and translates them into actual characters, which can then be embedded in the PDF itself as an invisible layer sitting on top of the image. The document still looks like the original scan, but now Ctrl+F can find a word inside it. Quality depends heavily on how sharp the original scan was.

← Back to the glossary

Necessary cookies. We use strictly necessary cookies for the quota and sign-in; we do not use analytics cookies. Your PDFs are processed in your browser, except in PDF to Word. Learn more