Enhanced OCR Quality for PDF to OCR

PDF to OCR gains the OcrQuality parameter, so the enhanced engine that reads low quality scans, small print and rotated text much better is now available for PDFs too, as it already was for JPG to TXT, PNG to TXT and TIFF to TXT.

Highlights

• Enhanced quality is now available for PDF to OCR, not only for image OCR.
• Arabic and Greek join the languages the enhanced engine reads.
• PDF to OCR with text output now honors OcrMode auto: pages that already contain text return their own text and only pages without text are recognized.

Parameters

• OcrQuality (collection, default fast) on PDF to OCR - fast for the classic engine, enhanced for the new one.

Try it out

• PDF to OCR
• API sandbox: pdf-to-ocr
• JPG to TXT