Motion-Based Handwriting Recognition

2021/01/15 by Junshen Kevin Chen, Chen, Junshen Kevin, Wanze Xie +3 · 4 citations
Computer Science · Engineering · Neuroscience · #Artificial intelligence #Computer science #Computer vision #Engineering #Feature extraction #Gyroscope #Hand Gesture Recognition Systems #Handwriting #Handwriting recognition #Handwritten Text Recognition Techniques #Motion (physics) #Pattern recognition (psychology) #Reading (process) #Speech recognition #Stylus #Tactile and Sensory Interactions #cs.AI #cs.CV

paper · pdf · doi:10.48550/arxiv.2101.06022

published in arXiv (Cornell University) (Cornell University)

arxiv created 2021/01/15 · arxiv updated 2021/01/18

Abstract

We attempt to overcome the restriction of requiring a writing surface for handwriting recognition. In this study, we design a prototype of a stylus equipped with motion sensor, and utilizes gyroscopic and acceleration sensor reading to perform written letter classification using various deep learning techniques such as CNN and RNNs. We also explore various data augmentation techniques and their effects, reaching up to 86% accuracy.

Citations

• Gradient-based learning applied to document recognition
• Nearest neighbor pattern classification

Related

• Motion-Based Handwriting Recognition and Word Reconstruction
• Towards an IMU-based Pen Online Handwriting Recognizer
• Online Handwriting Trajectory Reconstruction from Kinematic Sensors using Temporal Convolutional Network
• An inclusive review on deep learning techniques and their scope in handwriting recognition
• Domain Adaptation for Handwriting Trajectory Reconstruction from IMU Sensors