期刊
出版社
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3411842
关键词
Online handwriting recognition; character dataset; inertial measurement unit; time-series data; sensor-based pen; writer-(in)dependent; multi-stroke gestures; embedded
资金
- Federal Ministry of Education and Research (BMBF) of Germany [16SV8228]
- Bayerisches Staatsministerium fur Wirtschaft, Landesentwicklung und Energie [IUK-1902-0004]
This paper presents a handwriting recognition (HWR) system that deals with online character recognition in real-time. Our sensor-enhanced ballpoint pen delivers sensor data streams from triaxial acceleration, gyroscope, magnetometer and force signals at 100 HZ. As most existing datasets do not meet the requirements of online handwriting recognition and as they have been collected using specific equipment under constrained conditions, we propose a novel online handwriting dataset acquired from 119 writers consisting of 31,275 uppercase and lowercase English alphabet character recordings (52 classes) as part of the UbiComp 2020 Time Series Classification Challenge. Our novel OnHW-chars dataset allows for the evaluations of uppercase, lowercase and combined classification tasks, on both writer-dependent (WD) and writer-independent (WI) classes and we show that properly tuned machine learning pipelines as well as deep learning classifiers (such as CNNs, LSTMs, and BiLSTMs) yield accuracies up to 90 % for the WD task and 83 % for the WI task for uppercase characters. Our baseline implementations together with the rich and publicly available OnHW dataset serve as a baseline for future research in that area.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据