Table Parsing

This repository implements computer vision based approaches for detecting and parsing visual features such as tables or previous redactions in PDFs.

Installation

git clone ssh://git@git.iqser.com:2222/rr/table_parsing.git
cd table_parsing

python -m venv env
source env/bin/activate

pip install -e .
pip install -r requirements.txt

Usage

# Parse tables on second page of a PDF
python scripts/annotate.py <path to pdf> 1 --type table

# Detect redactions (black filled rectangles) on first page of a PDF
python scripts/annotate.py <path to pdf> 0 --type redaction