https://github.com/sdpdas/document-layout-generator-and-segmentation-tool

Lists all parts of a document PDF and is a highly scalable with robust code.
https://github.com/sdpdas/document-layout-generator-and-segmentation-tool

analysis document-classification numpy opencv-python pdf2image python

Last synced: 10 days ago
JSON representation

Lists all parts of a document PDF and is a highly scalable with robust code.

• Host: GitHub
• URL: https://github.com/sdpdas/document-layout-generator-and-segmentation-tool
• Owner: SDpDas
• Created: 2024-06-23T21:16:40.000Z (6 months ago)
• Default Branch: main
• Last Pushed: 2024-06-24T08:04:06.000Z (6 months ago)
• Last Synced: 2024-06-24T22:51:56.730Z (6 months ago)
• Topics: analysis, document-classification, numpy, opencv-python, pdf2image, python
• Language: Python
• Homepage:
• Size: 58.7 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Document Layout Generation 

Note - Install necessary libraries such as opencv-python, pdf2image, img2pdf, numpy etc.

       Download Poppler https://github.com/oschwartz10612/poppler-windows/releases/

## Description

This tool converts any document PDF to its segmented version PDF. 

All middle work can be found in input and output image folder.

## How to Use?

1. Download the ZIP file of the project and open its source folder.

2. Navigate to layout.py and run it directly or by using 

    ```python

    python layout.py

3. If you want to use your own document add it to folder and change the path in layout.py

    ```python

    pdf_file = '...\\(PDF_name).pdf'

4. Observe the results in Processed Files folder.

## Glossary

1. input_img : will show all images in openCV format when extracted from PDF. 

2. output_img : will show all output images after resizing and object detection is done.

3. output_pdf : will display the resultant PDFs of merged output images.

# Screenshots:

![arxiv1](working/output_1.png)

![arxiv1](working/output_2.png)

# Created by Sagardeep Das