Enhancing Document Key Information Localization Through Data Augmentation

TL;DR

This paper introduces a data augmentation approach that improves the localization of key information in both digital and handwritten document images by mimicking handwriting styles, enhancing model generalization.

Contribution

The paper proposes a novel augmentation method that simulates handwritten documents to train models for key information localization, without using handwritten data in training.

Findings

Augmentation improves model generalization to handwritten documents.

The approach achieves high performance in the VRDIU Track B competition.

Simple augmentation significantly enhances localization accuracy.

Abstract

The Visually Rich Form Document Intelligence and Understanding (VRDIU) Track B focuses on the localization of key information in document images. The goal is to develop a method capable of localizing objects in both digital and handwritten documents, using only digital documents for training. This paper presents a simple yet effective approach that includes a document augmentation phase and an object detection phase. Specifically, we augment the training set of digital documents by mimicking the appearance of handwritten documents. Our experiments demonstrate that this pipeline enhances the models' generalization ability and achieves high performance in the competition.