Handwritten text generation and strikethrough characters augmentation
Alex Shonenkov, Denis Karachev, Max Novopoltsev, Mark Potanin, Denis, Dimitrov, Andrey Chertok

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
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHandwritten Text Recognition Techniques · Natural Language Processing Techniques · Topic Modeling
