Motion-Based Handwriting Recognition
This addresses the need for surface-independent handwriting input for users in mobile or constrained environments, but it is incremental as it builds on existing sensor and deep learning methods.
The researchers tackled the problem of handwriting recognition without a writing surface by developing a motion-sensor-equipped stylus prototype, achieving up to 86% accuracy using deep learning techniques like CNNs and RNNs.
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.