Tokenization vs. Augmentation: A Systematic Study of Writer Variance in IMU-Based Online Handwriting Recognition
This work addresses writer variability in handwriting recognition, offering practical strategies for improving accuracy in applications like digital pens, but it is incremental as it builds on existing methods for a specific domain.
The study tackled inter-writer and intra-writer variability in IMU-based online handwriting recognition by comparing sub-word tokenization and concatenation-based data augmentation, finding that tokenization reduced word error rate from 15.40% to 12.99% for unseen writing styles while augmentation reduced character error rate by 34.5% and word error rate by 25.4% for known writers.
Inertial measurement unit-based online handwriting recognition enables the recognition of input signals collected across different writing surfaces but remains challenged by uneven character distributions and inter-writer variability. In this work, we systematically investigate two strategies to address these issues: sub-word tokenization and concatenation-based data augmentation. Our experiments on the OnHW-Words500 dataset reveal a clear dichotomy between handling inter-writer and intra-writer variance. On the writer-independent split, structural abstraction via Bigram tokenization significantly improves performance to unseen writing styles, reducing the word error rate (WER) from 15.40% to 12.99%. In contrast, on the writer-dependent split, tokenization degrades performance due to vocabulary distribution shifts between the training and validation sets. Instead, our proposed concatenation-based data augmentation acts as a powerful regularizer, reducing the character error rate by 34.5% and the WER by 25.4%. Further analysis shows that short, low-level tokens benefit model performance and that concatenation-based data augmentation performance gain surpasses those achieved by proportionally extended training. These findings reveal a clear variance-dependent effect: sub-word tokenization primarily mitigates inter-writer stylistic variability, whereas concatenation-based data augmentation effectively compensates for intra-writer distributional sparsity.