Finger Joint Angle and Gesture Estimation Under Dynamic Hand Position Using a Soft Printed Electrode Array.

The pursuit of innovative methods for finger gesture recognition has been an area of active research, with particular emphasis on surface electromyography (sEMG) due to its potential in human-machine interface (HMI) applications, especially in scenarios where visual imaging is impractical. EMG is a promising approach for gesture recognition, but is highly susceptible to movement artifacts, individual motor variability, and changes in hand position, making gesture recognition challenging during dynamic hand movements. While progress has been made in EMG data collection and analysis, most studies focus on controlled, static hand positions, limiting real-world applicability. This study integrates a soft wearable sEMG sensor, a Video-Vision-Transform model, and motion sensor-based training to enhance finger joint angle prediction and gesture recognition across static and dynamic hand positions. Results show substantial variability among participants, yet demonstrate the ability to reach excellent differentiation of finger angles and gestures. For highly performing participants (N=16), recognition accuracy reached 0.85 for static and 0.87 for dynamic conditions. This work advances EMG-based gesture recognition, supporting more robust, real-world applications in dynamic environments.Clinical relevance- Accurate finger gesture recognition using soft wearable EMG sensors has significant implications for neurorehabilitation and assistive technologies. It may enhance motor function assessment, facilitate personalized rehabilitation, and improve prosthetic control by enabling intuitive human-machine interactions. By addressing user variability and optimizing recognition in dynamic conditions, this study contributes to next-generation wearable neurotechnology for neuromuscular disorders, stroke, and spinal cord injuries.