Autotag a PDF with DeepDoctection

Autotag a PDF with DeepDoctection

DeepDoctection is a toolbox designed to make it easier to start working on this topic.

DeepDoctection is a Python package that allows the creation of document extraction analysis and document layout analysis tasks by using deep learning models. It focuses on applications related to document extraction from PDFs or scans in various image formats. Deepdoctection provides model wrappers for various tasks to be integrated into pipelines.

A picture shows an output of the process deepdoctection - document extraction and layout analysis.
Output as a Layout Detection

PDFix – Autotag – DeepDoctection

Our example of auto-tagging PDF documents with PDFix SDK and the deepdoctection python AI library for document extraction and layout analysis is now available on GitHub.

LINK: https://github.com/pdfix/pdfix-autotag-deepdoctection

Use Layout Recognition Results to Create Accessible PDF

Test an example of auto-tagging PDF document with PDFix SDK and the deepdoctection Python AI library for document extraction and layout analysis available at Huggingface.

LINK: https://huggingface.co/spaces/deepdoctection/deepdoctection

Deepdoctection is supported on macOS/Linux.

How-to:

Installation

Create a virtual Python environment

python3 -m venv env && source env/bin/activate

Install the PDFix SDK package

pip install pdfix-sdk

To install deepdoctection library follow the steps on https://github.com/deepdoctection/deepdoctection#installation

Run the example

To run the example execute

python3 autotag.py

Thank you for visiting our Blog. If you have any questions or comments, please do not hesitate to contact us.


You might also like