An Imu-Based Wearable Ring For On-Surface Handwriting Recognition

We propose a finger-worn, on-surface fingerwriting recognition system based on an inertial sensor. The acceleration and the angular velocity data from the finger are sent by Bluetooth (BLE) to a host computer for conversion into words. The motion data are segmented by a long short-term memory (LSTM) model before recognition by a Convolutional Neural Network (CNN) or an LSTM model. Experiment results show the proposed system achieves 1.05% CER and 7.28% WER, making it a viable system as a text input interface.