docling-project / docling-project/docling
Backend for PDF OCR
Open
question
- Dominant language
- Python
- Stars
- 66.4k
- Forks
- 4.8k
- Avg merge
- 2d 21h
- Merged PRs (30d)
- 84
Description
### Question
I am currently implementing a pipeline with Docling Conversion of various formats.
However, I am confused about what backend to use in PDFs and image format documents. What I need is :
1. Better OCR
2. Accurately parse the tables.
3. Able to handle handwritten notes and cursive writing
Currently, I am using Rapid OCR with PyPdfiumDocumentBackend. I am not getting better results with handwritten notes.
...
Contributor guide
Assessment
This issue has not been assessed yet.