The OnHW Dataset: Online Handwriting Recognition from IMU-Enhanced Ballpoint Pens with Machine Learning
| Autor: | Felix Ott, Jens Barth, Mohamad Wehbi, Björn M. Eskofier, Tim Hamann, Christopher Mutschler |
|---|---|
| Přispěvatelé: | Publica |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Ubiquitous computing
Computer Networks and Communications Data stream mining business.industry Character (computing) Computer science Deep learning 020207 software engineering 02 engineering and technology Machine learning computer.software_genre Task (project management) Human-Computer Interaction Hardware and Architecture Inertial measurement unit Handwriting recognition Handwriting 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business computer |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|