Redact scanned PDF files with OCR
Find and redact text in scanned PDFs, then review the page images before export.
Why scanned documents need OCR
A scan contains pixels rather than ordinary selectable text. OCR finds words and their positions so matching names and phrases can be covered.
Start with a legible scan
Upload the clearest original available. Small text, rotation, low contrast and compression can cause missed words. Enlarging an already blurred scan cannot recover missing detail.
Review detected regions
Compare the original and redacted page. Add manual boxes over missed details and restore technical notes that should remain. Automatic detection is a starting point for review.
Check the output
The export check runs OCR on the result to look for target text. A clean check means that this check did not find the selected text; it is not proof that every sensitive detail was detected.