<ul data-eligibleForWebStory="false"><li>Online handwriting recognition (HWR) using data from inertial measurement units (IMUs) poses challenges due to writing style variations and limited annotated datasets.</li><li>This paper introduces an HWR model focused on improving writer-independent (WI) recognition on IMU data, employing a CNN encoder and a BiLSTM-based decoder.</li><li>The model exhibits robustness to unseen handwriting styles, surpassing existing methods on WI splits of public datasets with low character error rates (CERs) and word error rates (WERs).</li><li>Extensive evaluation demonstrates its adaptability to different age groups and efficiency through design choices, hinting at the potential for more adaptable and scalable HWR systems.</li></ul>

Robust and Efficient Writer-Independent IMU-Based Handwriting Recognition

Discover more