Vidocp

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

Installation

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

python -m venv env
source env/bin/activate

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

Usage

As an API

The module provided functions for the individual tasks that all return some kid of collection of points, depending on the specific task. Example for finding the outlines of previous redactions.

from vidocp.redaction_detection import find_redactions
import pdf2image 
import numpy as np

pdf_path = ...
page_index = ...


page = pdf2image.convert_from_path(pdf_path, first_page=page_index, last_page=page_index)[0]
page = np.array(page)

redaction_contours = find_redactions(page)

Example outputs from demo script:

Table parsing

The tables parsing utility detects and segments tables into individual cells.

python scripts/annotate.py <path to pdf> 1 --type table

Detect redactions

The redaction detection utility detects previous redactions in PDFs (black filled rectangles).

python scripts/annotate.py <path to pdf> 0 --type redaction

The below image shows the detected redactions with green outlines.