You are currently not logged in. Plaese login or register...
Our project mainly focus on to parse PDF documents (human risk assessment files) into structured, searchable data.
Specifically, we extract structured information from tables using text parsing and Computer Vision approach, and store the output in a structured way.
Using such structured data, we build into this searchable database.
agressively match any input with the raw content of the PDF document
similar to Advanced Search but with more refined, detailed results
combines filters (by endpoint/profile table) and text
each returned result is a row of table
results are exportable in csv file