About:

PDFigCapX is an online system for extracting figures and captions from biomedical documents. PDFigCapX takes the PDF file as input and generates files containing figures and captions, along with their position information on the corresponding PDF page as output.




Features:

  • Work effectively over biomedical documents containing complex figures and captions.
  • Robust in the face of different PDF versions.
  • High recall and precision for figure, caption, and figure-caption pair extraction.
  • Results are downloadable as a zip file.

    • Copyright © 2018 PDFigCapX, Computational Biomedicine Lab. All rights reserved.