Handwritten text generation and strikethrough characters augmentation

TL;DR

This paper presents two novel data augmentation techniques, HandWritten Blots and StackMix, that significantly improve handwritten text recognition accuracy across multiple datasets by simulating strikethroughs and generating synthetic handwritten text.

Contribution

The paper introduces two new augmentation methods for HTR that are effective across different network architectures and datasets, advancing state-of-the-art results.

Findings

Both augmentations reduce WER and CER significantly.

Techniques are effective across ten diverse datasets.

Augmentations are network-agnostic and broadly applicable.

Abstract

We introduce two data augmentation techniques, which, used with a Resnet-BiLSTM-CTC network, significantly reduce Word Error Rate (WER) and Character Error Rate (CER) beyond best-reported results on handwriting text recognition (HTR) tasks. We apply a novel augmentation that simulates strikethrough text (HandWritten Blots) and a handwritten text generation method based on printed text (StackMix), which proved to be very effective in HTR tasks. StackMix uses weakly-supervised framework to get character boundaries. Because these data augmentation techniques are independent of the network used, they could also be applied to enhance the performance of other networks and approaches to HTR. Extensive experiments on ten handwritten text datasets show that HandWritten Blots augmentation and StackMix significantly improve the quality of HTR models