OCR treaty pdfs - Githubissues

globalgov / manypkgs

Support for creating new manyverse packages

https://globalgov.github.io/manypkgs/

GNU Affero General Public License v3.0

2 stars 0 forks source link

OCR treaty pdfs #18

Closed jhollway closed 2 years ago

jhollway commented 3 years ago

Consider image binarization for removing grayscale elements from scanned text for improved optical character recognition.

How does quanteda do this?

jhollway commented 3 years ago

{pdftools}, {tesseract}, or both?

https://www.r-bloggers.com/2016/08/extracting-content-from-pdf-files/
https://www.r-bloggers.com/2019/03/get-text-from-pdfs-or-images-using-ocr-a-tutorial-with-tesseract-and-magick/
https://www.r-bloggers.com/2017/07/how-to-do-optical-character-recognition-ocr-of-non-english-documents-in-r-using-tesseract/

henriquesposito commented 2 years ago

@jhollway do you have any specific examples of datasets you want to incorporate that have their treaty texts in pdf formats? I will start to work on a function for OCR pdf texts. Thank you.

jhollway commented 2 years ago

ECOLEX has PDFs.