Re:Table Detection and Extraction Using Deep Learning
by jjohansson on Wednesday January 22, 2020 @12:23PM
(#22119675)
Disclaimer: I work for PDFTron
This is a very interesting field, and PDFTron has been doing similar work with ML and table extraction as part of our document understanding platform. We've made pretty good progress over the past year -- you can try it on your docs here:
This is a very interesting field, and PDFTron has been doing similar work with ML and table extraction as part of our document understanding platform. We've made pretty good progress over the past year -- you can try it on your docs here:
https://www.pdftron.com/pdf-tools/pdf-table-extraction/
We also have a rules-based table extraction product (PDFGenie) that works reasonably well, but ML is most definitely the future.