Mouseless Mouse

Individuals with limited hand mobility face issues in technology interactions. To address this, technology for interaction with machines has been developed. The invention uses a webcam for commands and face mesh technology to map facial features accurately and translate head movements into cursor movements. The data is amplified while allowing the maintenance of comfortable movement. Exponential moving average (EMA) was used to improve cursor control by giving more weight to recent data points, thus reducing jitter. The predictive capabilities of the Kalman filter are utilised, which enables accurate real-time cursor movements. Eye wink detection utilises eye-aspect ratio to accurately measure eye wink representation. To execute commands, a specialised Vision in Transformer model for detecting facial gestures has been developed.