Hand gesture recognition has become an essential field in computer vision, enabling natural and intuitive communication between humans and machines. In this project, we developed a lightweight system capable of recognizing static hand gestures in real time from a webcam feed. The method relies on MediaPipe Hands for landmark extraction and a fully connected neural network trained on normalized three-dimensional coordinates of 21 keypoints. Our approach emphasizes efficiency and accessibility by reducing data dimensionality and avoiding the need for complex image-based models. The resulting system achieves high accuracy for multiple gesture classes and can be applied to educational or assistive technologies such as sign language learning tools.
- On the fractal complexity of sacrum motion during walking
- Antoine Dufourneau - EuroMov Digital Health in MotionNicolas Sutton-Charani - Université de Montpellier, EuroMov DHM - EuroMov Digital Health in MotionLoic Damm - Université de Montpellier, EuroMov DHM - EuroMov Digital Health in MotionGuillaume Tallon - BeatHealthHubert Blain - CHU Montpellier = Montpellier University Hospital
- MOCO '26 - The 10th International Conference on Movement and Computing 2026 (Montpellier, France, 23/04/2026–25/04/2026)
- 99243398709311
- EuroMov DHM - EuroMov Digital Health in Motion
- English
- Conference proceeding
- hal-05627869