Follow the following step to run the pipeline in its entirity.

1. downloading_arxiv.py

2. filtering_pdf.py

3. extracting_imgs.md

4. crop2pdf.py

5. isLine.py

6. conda install -c conda-forge pdf2svg

7. Run pdf2svg.py (It also matches IDs with isLine)

8. svg2time_series.py (still pending)