Spaces:
Running
Running
Extracting Tables from PDFs without Extra Content: Using Table Transformer for Accurate Recognition
#1
by
ashanq
- opened
I have uploaded an image that contains extra content along with the table. However, it extracts other text from the PDF file as well. I think you should add a Table Transformer to first recognize the table, and then you can extract the table into HTML or any other format.
ashanq
changed discussion title from
Extracting Tables from PDFs with Extra Content: Using Table Transformer for Accurate Recognition
to Extracting Tables from PDFs without Extra Content: Using Table Transformer for Accurate Recognition
actually, there is a repo https://huggingface.co/spaces/Joker1212/RapidTableDetection for table extraction
for pdf, we also has layout repo https://github.com/RapidAI/RapidLayout with many onnx model,easy to use