English

Motion-Based Handwriting Recognition and Word Reconstruction

Computer Vision and Pattern Recognition 2021-01-18 v1

Abstract

In this project, we leverage a trained single-letter classifier to predict the written word from a continuously written word sequence, by designing a word reconstruction pipeline consisting of a dynamic-programming algorithm and an auto-correction model. We conduct experiments to optimize models in this pipeline, then employ domain adaptation to explore using this pipeline on unseen data distributions.

Keywords

Cite

@article{arxiv.2101.06025,
  title  = {Motion-Based Handwriting Recognition and Word Reconstruction},
  author = {Junshen Kevin Chen and Wanze Xie and Yutong He},
  journal= {arXiv preprint arXiv:2101.06025},
  year   = {2021}
}
R2 v1 2026-06-23T22:11:47.449Z