OCR
Closed this issue · 3 comments
Madhour commented
- Run OCR on PDF
- Layout detection (?)
- Structure text
yellowsh29 commented
PyPDF2 did not yield intended results.
First working implementation w/ PDF-Miner (non-ocr approach) 06eca99.
- Recognizes PDF structure (e.g., column-orientation)
Source = https://github.com/zoumdatascience/Natural-Language-Processing/blob/master/getPDFContent.ipynb
BennerLukas commented
done with pdf-miner
BennerLukas commented
