A scan is a picture of words. Until it is read, nobody can search it, copy a clause from it or find it a year later. Joy’s OCR (optical character recognition) reads Hebrew and English text in scanned PDFs and images and turns it into real text.
For PDFs, Joy adds an invisible text layer on top of each page, so the document looks exactly the same but becomes searchable. The recognised text also goes into Joy’s document search, so the scan turns up when you look for a name, a number or a clause.
What you can do
- Hebrew and English text recognition, mixed on the same page
- Searchable PDF: an invisible text layer over the original page
- Images (JPG, PNG) and scanned multi-page PDFs
- A confidence score for each page, so weak scans are easy to spot
- Recognised text added to search across all your documents
- OCR inside the PDF editor and the court bundle builder