| Abstract | Handwriting recognition technology allows recognizing a written text from a given data. The recognition task can target letters, symbols, or words, and the input data can be a digital image or recorded by various sensors. Over the years, there has been an increasing interest in experimenting with different types of technology to collect handwriting data, create datasets, and develop algorithms to recognize characters and symbols. More recently, the OnHW-chars dataset has been published that contains multivariate time series data of the English alphabet collected using a ballpoint pen fitted with sensors. The authors of OnHW-chars also provided some baseline results through their machine learning (ML) and deep learning (DL) classifiers. In this paper, we develop handwriting recognition models on the OnHW-chars dataset and improve the accuracy of previous models. More specifically, our ML models provide 11.3–23.56% improvements over the previous ML models, and our optimized DL models with ensemble learning provide 3.08–7.01% improvements over the previous DL models. In addition to our accuracy improvements over the spectrum, we aim to provide some level of explainability, using a specialized version of LIME, for our models to provide more logic behind chosen methods and why the models make sense for the data type in the dataset, as well as provide some explanation as to why ensemble methods may lead to an advantage in accuracy rates. In order to verify the robustness of our models trained over the OnHW-chars dataset, we trained our DL models using the same model parameters over a more recently published OnHW-equations dataset. Our DL models with ensemble learning provide 0.05–4.75% improvements over the previous DL models. Our results are verifiable and reproducible via the provided public repository. |
|---|
