Rotation-free Online Handwritten Character Recognition Using Linear Recurrent Units
This work addresses a practical challenge in handwriting recognition for applications like mobile input, but it is incremental as it builds on existing methods with a hybrid approach.
The paper tackled the problem of rotational deformations reducing accuracy in online handwritten character recognition by using Sliding Window Path Signature (SW-PS) for local structural features and Linear Recurrent Units (LRU) as a classifier, achieving accuracies of 99.62%, 96.67%, and 94.33% on rotated datasets.
Online handwritten character recognition leverages stroke order and dynamic features, which generally provide higher accuracy and robustness compared with offline recognition. However, in practical applications, rotational deformations can disrupt the spatial layout of strokes, substantially reducing recognition accuracy. Extracting rotation-invariant features therefore remains a challenging open problem. In this work, we employ the Sliding Window Path Signature (SW-PS) to capture local structural features of characters, and introduce the lightweight Linear Recurrent Units (LRU) as the classifier. The LRU combine the fast incremental processing capability of recurrent neural networks (RNN) with the efficient parallel training of state space models (SSM), while reliably modelling dynamic stroke characteristics. We conducted recognition experiments with random rotation angle up to $\pm 180^{\circ}$ on three subsets of the CASIA-OLHWDB1.1 dataset: digits, English upper letters, and Chinese radicals. The accuracies achieved after ensemble learning were $99.62\%$, $96.67\%$, and $94.33\%$, respectively. Experimental results demonstrate that the proposed SW-PS+LRU framework consistently surpasses competing models in both convergence speed and test accuracy.