cloud_upload

Drop files here or click to upload

Loading...

Select languages that are to be detected within the PDF (Ones listed are the ones currently detected):

---

eng

---

OCR Mode Ignores pages that have interactive text on them, only OCRs pages that are images Force OCR, will OCR Every page removing all original text elements Normal (Will error if PDF contains text)

Additional Settings

Produce text file containing OCR text alongside the OCR'ed PDF

Correct pages were scanned at a skewed angle by rotating them back into place

Clean page so its less likely that OCR will find text in background noise. (No output change)

Clean page so its less likely that OCR will find text in background noise, maintains cleanup in output.

Remove images after OCR (Removes ALL images, only useful if part of conversion step)

Render Type (Advanced) HOCR (Latin/Roman alphabet only) Sandwich

Process PDF with OCR

This service uses OCRmyPDF and Tesseract for OCR.

Please read this documentation on how to use this for other languages and/or use not in docker

https://github.com/Stirling-Tools/Stirling-PDF/blob/main/HowToUseOCR.md