Handwriting Recognition Based on 3D Accelerometer Data by Deep Learning
| Autor: | Juan Gabriel Avina-Cervantes, Carlos Rodrigo Correa-Cely, Jose Luis Contreras-Hernandez, Pedro López-Rodríguez, José Ruiz-Pinales |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2022 |
| Předmět: |
Fluid Flow and Transfer Processes
3D accelerometer data handwritten character recognition Convolutional Neural Networks (CNN) Long Short-Term Memory (LSTM) 3D signal processing Process Chemistry and Technology General Engineering General Materials Science Instrumentation Computer Science Applications |
| Zdroj: | Applied Sciences; Volume 12; Issue 13; Pages: 6707 |
| ISSN: | 2076-3417 |
| DOI: | 10.3390/app12136707 |
| Popis: | Online handwriting recognition has been the subject of research for many years. Despite that, a limited number of practical applications are currently available. The widespread use of devices such as smartphones, smartwatches, and tablets has not been enough to convince the user to use pen-based interfaces. This implies that more research on the pen interface and recognition methods is still necessary. This paper proposes a handwritten character recognition system based on 3D accelerometer signal processing using Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM). First, a user wearing an MYO armband on the forearm writes a multi-stroke freestyle character on a touchpad by using the finger or a pen. Next, the 3D accelerometer signals generated during the writing process are fed into a CNN, LSTM, or CNN-LSTM network for recognition. The convolutional backbone obtains spatial features in order to feed an LSTM that extracts short-term temporal information. The system was evaluated on a proprietary dataset of 3D accelerometer data collected from multiple users with an armband device, corresponding to handwritten English lowercase letters (a–z) and digits (0–9) in a freestyle. The results show that the proposed system overcomes other systems from the state of the art by 0.53%. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|