Augraphy: A Data Augmentation Library for Document Images

TL;DR

Augraphy is a Python library that creates realistic distortions in document images, enhancing data diversity for training and testing document image processing models.

Contribution

It introduces a versatile data augmentation library specifically designed for simulating real-world document image distortions.

Findings

Enables generation of diverse augmented document images

Improves robustness testing for document image models

Supports training for document denoising tasks

Abstract

This paper introduces Augraphy, a Python library for constructing data augmentation pipelines which produce distortions commonly seen in real-world document image datasets. Augraphy stands apart from other data augmentation tools by providing many different strategies to produce augmented versions of clean document images that appear as if they have been altered by standard office operations, such as printing, scanning, and faxing through old or dirty machines, degradation of ink over time, and handwritten markings. This paper discusses the Augraphy tool, and shows how it can be used both as a data augmentation tool for producing diverse training data for tasks such as document denoising, and also for generating challenging test data to evaluate model robustness on document image modeling tasks.