Motion-Based Handwriting Recognition and Word Reconstruction

TL;DR

This paper presents a novel handwriting recognition pipeline that combines a letter classifier, dynamic programming, and auto-correction to accurately reconstruct words from continuous handwriting, including adaptation to new data domains.

Contribution

It introduces an integrated pipeline for handwriting recognition that leverages domain adaptation and optimization techniques for improved accuracy.

Findings

Effective word reconstruction from continuous handwriting

Successful domain adaptation to unseen data

Enhanced accuracy through pipeline optimization

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.